Antoine Bordes


2020

pdf bib
Image-Chat: Engaging Grounded Conversations
Kurt Shuster | Samuel Humeau | Antoine Bordes | Jason Weston
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

To achieve the long-term goal of machines being able to engage humans in conversation, our models should captivate the interest of their speaking partners. Communication grounded in images, whereby a dialogue is conducted based on a given photo, is a setup naturally appealing to humans (Hu et al., 2014). In this work we study large-scale architectures and datasets for this goal. We test a set of neural architectures using state-of-the-art image and text representations, considering various ways to fuse the components. To test such models, we collect a dataset of grounded human-human conversations, where speakers are asked to play roles given a provided emotional mood or style, as the use of such traits is also a key factor in engagingness (Guo et al., 2019). Our dataset, Image-Chat, consists of 202k dialogues over 202k images using 215 possible style traits. Automatic metrics and human evaluations of engagingness show the efficacy of our approach; in particular, we obtain state-of-the-art performance on the existing IGC task, and our best performing model is almost on par with humans on the Image-Chat test set (preferred 47.7% of the time).

pdf bib
ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations
Fernando Alva-Manchego | Louis Martin | Antoine Bordes | Carolina Scarton | Benoît Sagot | Lucia Specia
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components, and/or delete information deemed unnecessary. Despite these varied range of possible text alterations, current models for automatic sentence simplification are evaluated using datasets that are focused on a single transformation, such as lexical paraphrasing or splitting. This makes it impossible to understand the ability of simplification models in more realistic settings. To alleviate this limitation, this paper introduces ASSET, a new dataset for assessing sentence simplification in English. ASSET is a crowdsourced multi-reference corpus where each simplification was produced by executing several rewriting transformations. Through quantitative and qualitative experiments, we show that simplifications in ASSET are better at capturing characteristics of simplicity when compared to other standard evaluation datasets for the task. Furthermore, we motivate the need for developing better methods for automatic evaluation using ASSET, since we show that current popular metrics may not be suitable when multiple simplification transformations are performed.

pdf bib
Controllable Sentence Simplification
Louis Martin | Éric de la Clergerie | Benoît Sagot | Antoine Bordes
Proceedings of the 12th Language Resources and Evaluation Conference

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same simplification is suitable for all; however multiple audiences can benefit from simplified text in different ways. We adapt a discrete parametrization mechanism that provides explicit control on simplification systems based on Sequence-to-Sequence models. As a result, users can condition the simplifications returned by a model on attributes such as length, amount of paraphrasing, lexical complexity and syntactic complexity. We also show that carefully chosen values of these attributes allow out-of-the-box Sequence-to-Sequence models to outperform their standard counterparts on simplification benchmarks. Our model, which we call ACCESS (as shorthand for AudienCe-CEntric Sentence Simplification), establishes the state of the art at 41.87 SARI on the WikiLarge test set, a +1.42 improvement over the best previously reported score.

pdf bib
Generating Fact Checking Briefs
Angela Fan | Aleksandra Piktus | Fabio Petroni | Guillaume Wenzek | Marzieh Saeidi | Andreas Vlachos | Antoine Bordes | Sebastian Riedel
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Fact checking at scale is difficult—while the number of active fact checking websites is growing, it remains too small for the needs of the contemporary media ecosystem. However, despite good intentions, contributions from volunteers are often error-prone, and thus in practice restricted to claim detection. We investigate how to increase the accuracy and efficiency of fact checking by providing information about the claim before performing the check, in the form of natural language briefs. We investigate passage-based briefs, containing a relevant passage from Wikipedia, entity-centric ones consisting of Wikipedia pages of mentioned entities, and Question-Answering Briefs, with questions decomposing the claim, and their answers. To produce QABriefs, we develop QABriefer, a model that generates a set of questions conditioned on the claim, searches the web for evidence, and generates answers. To train its components, we introduce QABriefDataset We show that fact checking with briefs — in particular QABriefs — increases the accuracy of crowdworkers by 10% while slightly decreasing the time taken. For volunteer (unpaid) fact checkers, QABriefs slightly increase accuracy and reduce the time required by around 20%.

2019

pdf bib
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
Angela Fan | Claire Gardent | Chloé Braud | Antoine Bordes
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input, long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved text portions.

pdf bib
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
Braden Hancock | Antoine Bordes | Pierre-Emmanuel Mazare | Jason Weston
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in. As our agent engages in conversation, it also estimates user satisfaction in its responses. When the conversation appears to be going well, the user’s responses become new training examples to imitate. When the agent believes it has made a mistake, it asks for feedback; learning to predict the feedback that will be given improves the chatbot’s dialogue abilities further. On the PersonaChat chit-chat dataset with over 131k training examples, we find that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision.

2018

pdf bib
Training Millions of Personalized Dialogue Agents
Pierre-Emmanuel Mazaré | Samuel Humeau | Martin Raison | Antoine Bordes
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Current dialogue systems fail at being engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models increases when conditioning them on text personas providing some personalized back-story to the model. However, the dataset used in Zhang et al. (2018) is synthetic and only contains around 1k different personas. In this paper we introduce a new dataset providing 5 million personas and 700 million persona-based dialogues. Our experiments show that, at this scale, training using personas still improves the performance of end-to-end systems. In addition, we show that other tasks benefit from the wide coverage of our dataset by fine-tuning our model on the data from Zhang et al. (2018) and achieving state-of-the-art results.

pdf bib
Reference-less Quality Estimation of Text Simplification Systems
Louis Martin | Samuel Humeau | Pierre-Emmanuel Mazaré | Éric de La Clergerie | Antoine Bordes | Benoît Sagot
Proceedings of the 1st Workshop on Automatic Text Adaptation (ATA)

2017

pdf bib
Reading Wikipedia to Answer Open-Domain Questions
Danqi Chen | Adam Fisch | Jason Weston | Antoine Bordes
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

This paper proposes to tackle open-domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

pdf bib
Proceedings of the 2nd Workshop on Representation Learning for NLP
Phil Blunsom | Antoine Bordes | Kyunghyun Cho | Shay Cohen | Chris Dyer | Edward Grefenstette | Karl Moritz Hermann | Laura Rimell | Jason Weston | Scott Yih
Proceedings of the 2nd Workshop on Representation Learning for NLP

pdf bib
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
Alexis Conneau | Douwe Kiela | Holger Schwenk | Loïc Barrault | Antoine Bordes
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.

pdf bib
ParlAI: A Dialog Research Software Platform
Alexander Miller | Will Feng | Dhruv Batra | Antoine Bordes | Adam Fisch | Jiasen Lu | Devi Parikh | Jason Weston
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

We introduce ParlAI (pronounced “par-lay”), an open-source software platform for dialog research implemented in Python, available at http://parl.ai. Its goal is to provide a unified framework for sharing, training and testing dialog models; integration of Amazon Mechanical Turk for data collection, human evaluation, and online/reinforcement learning; and a repository of machine learning models for comparing with others’ models, and improving upon existing architectures. Over 20 tasks are supported in the first release, including popular datasets such as SQuAD, bAbI tasks, MCTest, WikiQA, QACNN, QADailyMail, CBT, bAbI Dialog, Ubuntu, OpenSubtitles and VQA. Several models are integrated, including neural models such as memory networks, seq2seq and attentive LSTMs.

2016

pdf bib
Key-Value Memory Networks for Directly Reading Documents
Alexander Miller | Adam Fisch | Jesse Dodge | Amir-Hossein Karimi | Antoine Bordes | Jason Weston
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf bib
Composing Relationships with Translations
Alberto García-Durán | Antoine Bordes | Nicolas Usunier
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Fast Recursive Multi-class Classification of Pairs of Text Entities for Biomedical Event Extraction
Xiao Liu | Antoine Bordes | Yves Grandvalet
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

pdf bib
Question Answering with Subgraph Embeddings
Antoine Bordes | Sumit Chopra | Jason Weston
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

bib
Embedding Methods for Natural Language Processing
Antoine Bordes | Jason Weston
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Embedding-based models are popular tools in Natural Language Processing these days. In this tutorial, our goal is to provide an overview of the main advances in this domain. These methods learn latent representations of words, as well as database entries that can then be used to do semantic search, automatic knowledge base construction, natural language understanding, etc. Our current plan is to split the tutorial into 2 sessions of 90 minutes, with a 30 minutes coffee break in the middle, so that we can cover in a first session the basics of learning embeddings and advanced models in the second session. This is detailed in the following.Part 1: Unsupervised and Supervised EmbeddingsWe introduce models that embed tokens (words, database entries) by representing them as low dimensional embedding vectors. Unsupervised and supervised methods will be discussed, including SVD, Word2Vec, Paragraph Vectors, SSI, Wsabie and others. A comparison between methods will be made in terms of applicability, type of loss function (ranking loss, reconstruction loss, classification loss), regularization, etc. The use of these models in several NLP tasks will be discussed, including question answering, frame identification, knowledge extraction and document retrieval.Part 2: Embeddings for Multi-relational DataThis second part will focus mostly on the construction of embeddings for multi-relational data, that is when tokens can be interconnected in different ways in the data such as in knowledge bases for instance. Several methods based on tensor factorization, collective matrix factorization, stochastic block models or energy-based learning will be presented. The task of link prediction in a knowledge base will be used as an application example. Multiple empirical results on the use of embedding models to align textual information to knowledge bases will also be presented, together with some demos if time permits.

2013

pdf bib
Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction
Jason Weston | Antoine Bordes | Oksana Yakhnenko | Nicolas Usunier
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities
Xiao Liu | Antoine Bordes | Yves Grandvalet
Proceedings of the BioNLP Shared Task 2013 Workshop