[ACL2016]Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

Oct 26, 2016Download as pptx, pdf0 likes254 views

OgataTomoya

ACL読み会2016@小町研究室

Sequence-to-Sequence
Generation for Spoken Dialogue
via Deep Syntax Trees and Strings
Ondrˇej Dusˇek and Filip Jurcˇ ́ıcˇek
ACL, 2016
発表者 B4 尾形朋哉
1

概要
• seq2seqを用いて構文木だけではなく自然言語文を出力する手
法の提案
• 2stepによる生成と1stepによる手法の比較
• どちらの手法もとても少ないトレーニングデータで動作した
2

提案手法
• 入力：Dialogue Acts(DA)
• ２つの手法
1. 構文木を経由して自然言語文を出力
2. 直接自然言語文を出力
1はDAから構文木を出力し、構文木をTreex NLP toolkitの
surface realizerにより自然言語文に変換
2はDAから直接自然言語文を出力
4
Seq2seq Generator
Reranker
surface
realizer

提案手法
• 入力：Dialogue Acts(DA)
• ２つの手法
1. 構文木を経由して自然言語文を出力
2. 直接自然言語文を出力
1は複雑な表層構文などを人手で取り除き生成を簡単化できる
文法的正しさを常に保証できる
2のモードは構造を明示的にモデル化する必要がない
累積誤差を避けることができる
5
Seq2seq Generator
Reranker
surface
realizer

DA, deep syntax trees, 文の表現
• DAとdeep syntax treesと文をトークン列として表現する
• それぞれのトークンはembeddingとして表現される
• DAの表現列を形成するためにDAのそれぞれのスロットに対し
て”DA type, slot, value”の3つ組として表現
6

Seq2seq Generator
• Encoder
• Decoder
beam searchを行い、top-nの出力の対数尤度を保持する
7

Reranker
• n-best beam searchの出力に対してrerankし、情報抜けや不要
な情報を付加しているものにペナルティをかける
• 出力と入力のDAのベクトルのハミング距離でペナルティをかけ
る
• ペナルティがn-bestリストの対数尤度から引かれrerankされる
• Reranker
8

実験
• BAGEL data set
• restaurant information domainの202のDA
• それぞれ二つの言い換えがあり、それぞれを個々のものとして
扱った
• 181のトレーニングと21のテストに対して10分割交差検定を
行った
• Seq2seq GeneratorとRerankerはそれぞれAdam optimizerによ
り交差エントロピーを最小化するようにトレーニング
9

実験詳細
• レストランの名前や電話番号などは抽象化する
• 人手で付与されたスロットと値のアライメントは使用しなかっ
た
• データは小文字にし、文字列生成の際複数形のsは別のトーク
ンとして扱った
• 構造木を出力するモデルの学習のためにTreex NLP toolkitを用
いて構文木を獲得した
10

結果
• rerankerを用いない場合は2stepの手法の方が意味的誤りが少
なく、BLEU/NISTも高かった
• rerankerを用いるとjointモデルは2stepの手法と意味誤りの数
は同じで、BLEU/NISTは高くなった
11

結論
• 構文木を介した2ステップの手法と直接文字列を生成する手法
を比較した。
• それぞれ一定の性能を見せたが、それらの出力はかなり違うも
のとなった。
• 直接文字列を生成する手法の方がより好ましく、nグラムベー
スのものよりもかなり高いスコアと同程度の意味的誤りになっ
た
• RNNベースの手法で用いられるものよりもかなり小さいトレー
ニングデータで意味のある発話を出力するよう学習できた。
13

E. Shutova, D. Kiela, and J. Maillard. Black holes and white rabbits: Metaphor identification with visual features. In Proc. of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 160–170, San Diego, California, June 2016. Association for Computational Linguistics Abstract: Sarcasm is a peculiar form of sentiment expression, where the surface sentiment differs from the implied sentiment. The detection of sarcasm in social media platforms has been applied in the past mainly to textual utterances where lex- ical indicators (such as interjections and intensifiers), lin- guistic markers, and contextual information (such as user profiles, or past conversations) were used to detect the sarcastic tone. However, modern social media platforms allow to create multimodal messages where audiovisual content is integrated with the text, making the analysis of a mode in isolation partial. In our work, we first study the relation- ship between the textual and visual aspects in multimodal posts from three major social media platforms, i.e., Insta- gram, Tumblr and Twitter, and we run a crowdsourcing task to quantify the extent to which images are perceived as necessary by human annotators. Moreover, we propose two different computational frameworks to detect sarcasm that integrate the textual and visual modalities. The first approach exploits visual semantics trained on an external dataset, and concatenates the semantics features with state- of-the-art textual features. The second method adapts a visual neural network initialized with parameters trained on ImageNet to multimodal sarcastic posts. Results show the positive effect of combining modalities for the detection of sarcasm across platforms and methods.

Physical causality of action verbs in grounded language understandingFukumu Tsutsumi

The document discusses physical causality of action verbs in grounded language understanding. It describes how physical causality and change of state can be detected from video using semantic roles like agent, patient, source and destination. It also discusses two approaches - using rule-based knowledge or conditional random fields learning - to map semantic roles to tracks in video to understand verb causality grounded in physical events. The goal is to help machines understand language by grounding it in real-world physical interactions.

トピックモデルによる統計的潜在意味解析 2章後半Shinya Akiba

「トピックモデルによる統計的潜在意味解析」読書会 2章前半koba cky

Deep SimNetsFujimoto Keisuke

トピックモデルの話kogecoo

2024 Trend Updates: What Really Works In SEO & Content MarketingSearch Engine Journal

The future of SEO is trending toward a more human-first and user-centric approach, powered by AI intelligence and collaboration. Are you ready? Watch as we explore which SEO trends to prioritize to achieve sustainable growth and deliver reliable results. We’ll dive into best practices to adapt your strategy around industry-wide disruptions like SGE, how to navigate the top challenges SEO professionals are facing, and proven tactics for prioritizing quality and building trust. You’ll hear: - The top SEO trends to prioritize in 2024 to achieve long-term success. - Predictions for SGE’s impact, and how to adapt. - What E-E-A-T really means, and how to implement it holistically (hint: it’s never been more important). With Zack Kadish and Alex Carchietta, we’ll show you which SEO trends to ignore and which to focus on, along with the solution to overcoming rapid, significant and disruptive Google algorithm updates. If you’re looking to cut through the noise of constant SEO and content trends to drive success, you won’t want to miss this webinar.

Storytelling For The Web: Integrate Storytelling in your Design ProcessChiara Aliotta

Artificial Intelligence, Data and Competition – SCHREPEL – June 2024 OECD dis...OECD Directorate for Financial and Enterprise Affairs

This presentation by Thibault Schrepel, Associate Professor of Law at Vrije Universiteit Amsterdam University, was made during the discussion “Artificial Intelligence, Data and Competition” held at the 143rd meeting of the OECD Competition Committee on 12 June 2024. More papers and presentations on the topic can be found at oe.cd/aicomp. This presentation was uploaded with the author’s consent.

How to Leverage AI to Boost Employee Wellness - Lydia Di Francesco - SocialHR...SocialHRCamp

Speaker: Lydia Di Francesco In this workshop, participants will delve into the realm of AI and its profound potential to revolutionize employee wellness initiatives. From stress management to fostering work-life harmony, AI offers a myriad of innovative tools and strategies that can significantly enhance the wellbeing of employees in any organization. Attendees will learn how to effectively leverage AI technologies to cultivate a healthier, happier, and more productive workforce. Whether it's utilizing AI-powered chatbots for mental health support, implementing data analytics to identify internal, systemic risk factors, or deploying personalized wellness apps, this workshop will equip participants with actionable insights and best practices to harness the power of AI for boosting employee wellness. Join us and discover how AI can be a strategic partner towards a culture of wellbeing and resilience in the workplace.

2024 State of Marketing Report – by HubspotMarius Sescu

https://www.hubspot.com/state-of-marketing · Scaling relationships and proving ROI · Social media is the place for search, sales, and service · Authentic influencer partnerships fuel brand growth · The strongest connections happen via call, click, chat, and camera. · Time saved with AI leads to more creative work · Seeking: A single source of truth · TLDR; Get on social, try AI, and align your systems. · More human marketing, powered by robots

Everything You Need To Know About ChatGPTExpeed Software

ChatGPT is a revolutionary addition to the world since its introduction in 2022. A big shift in the sector of information gathering and processing happened because of this chatbot. What is the story of ChatGPT? How is the bot responding to prompts and generating contents? Swipe through these slides prepared by Expeed Software, a web development company regarding the development and technical intricacies of ChatGPT!

Product Design Trends in 2024 | Teenage EngineeringsPixeldarts

How Race, Age and Gender Shape Attitudes Towards Mental HealthThinkNow

Mental health has been in the news quite a bit lately. Dozens of U.S. states are currently suing Meta for contributing to the youth mental health crisis by inserting addictive features into their products, while the U.S. Surgeon General is touring the nation to bring awareness to the growing epidemic of loneliness and isolation. The country has endured periods of low national morale, such as in the 1970s when high inflation and the energy crisis worsened public sentiment following the Vietnam War. The current mood, however, feels different. Gallup recently reported that national mental health is at an all-time low, with few bright spots to lift spirits. To better understand how Americans are feeling and their attitudes towards mental health in general, ThinkNow conducted a nationally representative quantitative survey of 1,500 respondents and found some interesting differences among ethnic, age and gender groups. Technology For example, 52% agree that technology and social media have a negative impact on mental health, but when broken out by race, 61% of Whites felt technology had a negative effect, and only 48% of Hispanics thought it did. While technology has helped us keep in touch with friends and family in faraway places, it appears to have degraded our ability to connect in person. Staying connected online is a double-edged sword since the same news feed that brings us pictures of the grandkids and fluffy kittens also feeds us news about the wars in Israel and Ukraine, the dysfunction in Washington, the latest mass shooting and the climate crisis. Hispanics may have a built-in defense against the isolation technology breeds, owing to their large, multigenerational households, strong social support systems, and tendency to use social media to stay connected with relatives abroad. Age and Gender When asked how individuals rate their mental health, men rate it higher than women by 11 percentage points, and Baby Boomers rank it highest at 83%, saying it’s good or excellent vs. 57% of Gen Z saying the same. Gen Z spends the most amount of time on social media, so the notion that social media negatively affects mental health appears to be correlated. Unfortunately, Gen Z is also the generation that’s least comfortable discussing mental health concerns with healthcare professionals. Only 40% of them state they’re comfortable discussing their issues with a professional compared to 60% of Millennials and 65% of Boomers. Race Affects Attitudes As seen in previous research conducted by ThinkNow, Asian Americans lag other groups when it comes to awareness of mental health issues. Twenty-four percent of Asian Americans believe that having a mental health issue is a sign of weakness compared to the 16% average for all groups. Asians are also considerably less likely to be aware of mental health services in their communities (42% vs. 55%) and most likely to seek out information on social media (51% vs. 35%).

AI Trends in Creative Operations 2024 by Artwork Flow.pdfmarketingartwork

Creative operations teams expect increased AI use in 2024. Currently, over half of tasks are not AI-enabled, but this is expected to decrease in the coming year. ChatGPT is the most popular AI tool currently. Business leaders are more actively exploring AI benefits than individual contributors. Most respondents do not believe AI will impact workforce size in 2024. However, some inhibitions still exist around AI accuracy and lack of understanding. Creatives primarily want to use AI to save time on mundane tasks and boost productivity.

Skeleton Culture CodeSkeleton Technologies

Organizational culture includes values, norms, systems, symbols, language, assumptions, beliefs, and habits that influence employee behaviors and how people interpret those behaviors. It is important because culture can help or hinder a company's success. Some key aspects of Netflix's culture that help it achieve results include hiring smartly so every position has stars, focusing on attitude over just aptitude, and having a strict policy against peacocks, whiners, and jerks.

PEPSICO Presentation to CAGNY Conference Feb 2024Neil Kimberley

PepsiCo provided a safe harbor statement noting that any forward-looking statements are based on currently available information and are subject to risks and uncertainties. It also provided information on non-GAAP measures and directing readers to its website for disclosure and reconciliation. The document then discussed PepsiCo's business overview, including that it is a global beverage and convenient food company with iconic brands, $91 billion in net revenue in 2023, and nearly $14 billion in core operating profit. It operates through a divisional structure with a focus on local consumers.

Content Methodology: A Best Practices Report (Webinar)contently

This document provides an overview of content methodology best practices. It defines content methodology as establishing objectives, KPIs, and a culture of continuous learning and iteration. An effective methodology focuses on connecting with audiences, creating optimal content, and optimizing processes. It also discusses why a methodology is needed due to the competitive landscape, proliferation of channels, and opportunities for improvement. Components of an effective methodology include defining objectives and KPIs, audience analysis, identifying opportunities, and evaluating resources. The document concludes with recommendations around creating a content plan, testing and optimizing content over 90 days.

How to Prepare For a Successful Job Search for 2024Albert Qian

The document provides guidance on preparing a job search for 2024. It discusses the state of the job market, focusing on growth in AI and healthcare but also continued layoffs. It recommends figuring out what you want to do by researching interests and skills, then conducting informational interviews. The job search should involve building a personal brand on LinkedIn, actively applying to jobs, tailoring resumes and interviews, maintaining job hunting as a habit, and continuing self-improvement. Once hired, the document advises setting new goals and keeping skills and networking active in case of future opportunities.

Social Media Marketing Trends 2024 // The Global Indie InsightsKurio // The Social Media Age(ncy)

A report by thenetworkone and Kurio. The contributing experts and agencies are (in an alphabetical order): Sylwia Rytel, Social Media Supervisor, 180heartbeats + JUNG v MATT (PL), Sharlene Jenner, Vice President - Director of Engagement Strategy, Abelson Taylor (USA), Alex Casanovas, Digital Director, Atrevia (ES), Dora Beilin, Senior Social Strategist, Barrett Hoffher (USA), Min Seo, Campaign Director, Brand New Agency (KR), Deshé M. Gully, Associate Strategist, Day One Agency (USA), Francesca Trevisan, Strategist, Different (IT), Trevor Crossman, CX and Digital Transformation Director; Olivia Hussey, Strategic Planner; Simi Srinarula, Social Media Manager, The Hallway (AUS), James Hebbert, Managing Director, Hylink (CN / UK), Mundy Álvarez, Planning Director; Pedro Rojas, Social Media Manager; Pancho González, CCO, Inbrax (CH), Oana Oprea, Head of Digital Planning, Jam Session Agency (RO), Amy Bottrill, Social Account Director, Launch (UK), Gaby Arriaga, Founder, Leonardo1452 (MX), Shantesh S Row, Creative Director, Liwa (UAE), Rajesh Mehta, Chief Strategy Officer; Dhruv Gaur, Digital Planning Lead; Leonie Mergulhao, Account Supervisor - Social Media & PR, Medulla (IN), Aurelija Plioplytė, Head of Digital & Social, Not Perfect (LI), Daiana Khaidargaliyeva, Account Manager, Osaka Labs (UK / USA), Stefanie Söhnchen, Vice President Digital, PIABO Communications (DE), Elisabeth Winiartati, Managing Consultant, Head of Global Integrated Communications; Lydia Aprina, Account Manager, Integrated Marketing and Communications; Nita Prabowo, Account Manager, Integrated Marketing and Communications; Okhi, Web Developer, PNTR Group (ID), Kei Obusan, Insights Director; Daffi Ranandi, Insights Manager, Radarr (SG), Gautam Reghunath, Co-founder & CEO, Talented (IN), Donagh Humphreys, Head of Social and Digital Innovation, THINKHOUSE (IRE), Sarah Yim, Strategy Director, Zulu Alpha Kilo (CA).

Trends In Paid Search: Navigating The Digital Landscape In 2024Search Engine Journal

The search marketing landscape is evolving rapidly with new technologies, and professionals, like you, rely on innovative paid search strategies to meet changing demands. It’s important that you’re ready to implement new strategies in 2024. Check this out and learn the top trends in paid search advertising that are expected to gain traction, so you can drive higher ROI more efficiently in 2024. You’ll learn: - The latest trends in AI and automation, and what this means for an evolving paid search ecosystem. - New developments in privacy and data regulation. - Emerging ad formats that are expected to make an impact next year. Watch Sreekant Lanka from iQuanti and Irina Klein from OneMain Financial as they dive into the future of paid search and explore the trends, strategies, and technologies that will shape the search marketing landscape. If you’re looking to assess your paid search strategy and design an industry-aligned plan for 2024, then this webinar is for you.

5 Public speaking tips from TED - Visualized summarySpeakerHub

From their humble beginnings in 1984, TED has grown into the world’s most powerful amplifier for speakers and thought-leaders to share their ideas. They have over 2,400 filmed talks (not including the 30,000+ TEDx videos) freely available online, and have hosted over 17,500 events around the world. With over one billion views in a year, it’s no wonder that so many speakers are looking to TED for ideas on how to share their message more effectively. The article “5 Public-Speaking Tips TED Gives Its Speakers”, by Carmine Gallo for Forbes, gives speakers five practical ways to connect with their audience, and effectively share their ideas on stage. Whether you are gearing up to get on a TED stage yourself, or just want to master the skills that so many of their speakers possess, these tips and quotes from Chris Anderson, the TED Talks Curator, will encourage you to make the most impactful impression on your audience. See the full article and more summaries like this on SpeakerHub here: https://speakerhub.com/blog/5-presentation-tips-ted-gives-its-speakers See the original article on Forbes here: http://www.forbes.com/forbes/welcome/?toURL=http://www.forbes.com/sites/carminegallo/2016/05/06/5-public-speaking-tips-ted-gives-its-speakers/&refURL=&referrer=#5c07a8221d9b

ChatGPT and the Future of Work - Clark Boyd Clark Boyd

Everyone is in agreement that ChatGPT (and other generative AI tools) will shape the future of work. Yet there is little consensus on exactly how, when, and to what extent this technology will change our world. Businesses that extract maximum value from ChatGPT will use it as a collaborative tool for everything from brainstorming to technical maintenance. For individuals, now is the time to pinpoint the skills the future professional will need to thrive in the AI age. Check out this presentation to understand what ChatGPT is, how it will shape the future of work, and how you can prepare to take advantage.

Getting into the tech field. what next Tessa Mero

The document provides career advice for getting into the tech field, including: - Doing projects and internships in college to build a portfolio. - Learning about different roles and technologies through industry research. - Contributing to open source projects to build experience and network. - Developing a personal brand through a website and social media presence. - Networking through events, communities, and finding a mentor. - Practicing interviews through mock interviews and whiteboarding coding questions.

Google's Just Not That Into You: Understanding Core Updates & Search IntentLily Ray

1. Core updates from Google periodically change how its algorithms assess and rank websites and pages. This can impact rankings through shifts in user intent, site quality issues being caught up to, world events influencing queries, and overhauls to search like the E-A-T framework. 2. There are many possible user intents beyond just transactional, navigational and informational. Identifying intent shifts is important during core updates. Sites may need to optimize for new intents through different content types and sections. 3. Responding effectively to core updates requires analyzing "before and after" data to understand changes, identifying new intents or page types, and ensuring content matches appropriate intents across video, images, knowledge graphs and more.

How to have difficult conversations Rajiv Jayarajah, MAppComm, ACC

Introduction to Data ScienceChristy Abraham Joy

Time Management & Productivity - Best PracticesVit Horky

[ACL2016]Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

1. Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings Ondrˇej Dusˇek and Filip Jurcˇ ́ıcˇek ACL, 2016 発表者 B4 尾形朋哉 1

2. 概要 • seq2seqを用いて構文木だけではなく自然言語文を出力する手法の提案 • 2stepによる生成と1stepによる手法の比較 • どちらの手法もとても少ないトレーニングデータで動作した 2

3. タスク 3 入力のDialogue actに対して自然言語文を出力

4. 提案手法 • 入力：Dialogue Acts(DA) • ２つの手法 1. 構文木を経由して自然言語文を出力 2. 直接自然言語文を出力 1はDAから構文木を出力し、構文木をTreex NLP toolkitの surface realizerにより自然言語文に変換 2はDAから直接自然言語文を出力 4 Seq2seq Generator Reranker surface realizer

5. 提案手法 • 入力：Dialogue Acts(DA) • ２つの手法 1. 構文木を経由して自然言語文を出力 2. 直接自然言語文を出力 1は複雑な表層構文などを人手で取り除き生成を簡単化できる文法的正しさを常に保証できる 2のモードは構造を明示的にモデル化する必要がない累積誤差を避けることができる 5 Seq2seq Generator Reranker surface realizer

6. DA, deep syntax trees, 文の表現 • DAとdeep syntax treesと文をトークン列として表現する • それぞれのトークンはembeddingとして表現される • DAの表現列を形成するためにDAのそれぞれのスロットに対して”DA type, slot, value”の3つ組として表現 6

7. Seq2seq Generator • Encoder • Decoder beam searchを行い、top-nの出力の対数尤度を保持する 7

8. Reranker • n-best beam searchの出力に対してrerankし、情報抜けや不要な情報を付加しているものにペナルティをかける • 出力と入力のDAのベクトルのハミング距離でペナルティをかける • ペナルティがn-bestリストの対数尤度から引かれrerankされる • Reranker 8

9. 実験 • BAGEL data set • restaurant information domainの202のDA • それぞれ二つの言い換えがあり、それぞれを個々のものとして扱った • 181のトレーニングと21のテストに対して10分割交差検定を行った • Seq2seq GeneratorとRerankerはそれぞれAdam optimizerにより交差エントロピーを最小化するようにトレーニング 9

10. 実験詳細 • レストランの名前や電話番号などは抽象化する • 人手で付与されたスロットと値のアライメントは使用しなかった • データは小文字にし、文字列生成の際複数形のsは別のトークンとして扱った • 構造木を出力するモデルの学習のためにTreex NLP toolkitを用いて構文木を獲得した 10

11. 結果 • rerankerを用いない場合は2stepの手法の方が意味的誤りが少なく、BLEU/NISTも高かった • rerankerを用いるとjointモデルは2stepの手法と意味誤りの数は同じで、BLEU/NISTは高くなった 11

12. 出力 12

13. 結論 • 構文木を介した2ステップの手法と直接文字列を生成する手法を比較した。 • それぞれ一定の性能を見せたが、それらの出力はかなり違うものとなった。 • 直接文字列を生成する手法の方がより好ましく、nグラムベースのものよりもかなり高いスコアと同程度の意味的誤りになった • RNNベースの手法で用いられるものよりもかなり小さいトレーニングデータで意味のある発話を出力するよう学習できた。 13

Editor's Notes

#7: seq2seqのgeneratorから出力された構造木は角括弧記法で表される
#9: Rerankerはdialogue actとslot valueの組があるかどうかを２値で出力する
#12: 加えてjointモデルは外部のsurface realizerを必要としない。
#13: 意味的に閉じたモノの混同が多く見られる。たとえばFrenchとすべきところをItalianとしてしまう with treesの方は構文的流暢性が低い、繰り返しが起きる

[ACL2016]Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

Recommended

More Related Content

Featured (20)

[ACL2016]Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

Editor's Notes