Stephen Roller


pdf bib
Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
Eric Smith | Orion Hsu | Rebecca Qian | Stephen Roller | Y-Lan Boureau | Jason Weston
Proceedings of the 4th Workshop on NLP for Conversational AI

At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016), with human evaluations still considered the gold standard. Unfortunately, how to perform human evaluations is also an open problem: differing data collection methods have varying levels of human agreement and statistical sensitivity, resulting in differing amounts of human annotation hours and labor costs. In this work we compare five different crowdworker-based human evaluation methods and find that different methods are best depending on the types of models compared, with no clear winner across the board. While this highlights the open problems in the area, our analysis leads to advice of when to use which one, and possible future directions.


pdf bib
Adding Chit-Chat to Enhance Task-Oriented Dialogues
Kai Sun | Seungwhan Moon | Paul Crook | Stephen Roller | Becka Silvert | Bing Liu | Zhiguang Wang | Honglei Liu | Eunjoon Cho | Claire Cardie
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging conversations. In this work, we propose to integrate both types of systems by Adding Chit-Chat to ENhance Task-ORiented dialogues (ACCENTOR), with the goal of making virtual assistant conversations more engaging and interactive. Specifically, we propose a Human <-> AI collaborative data collection approach for generating diverse chit-chat responses to augment task-oriented dialogues with minimal annotation effort. We then present our new chit-chat-based annotations to 23.8K dialogues from two popular task-oriented datasets (Schema-Guided Dialogue and MultiWOZ 2.1) and demonstrate their advantage over the originals via human evaluation. Lastly, we propose three new models for adding chit-chat to task-oriented dialogues, explicitly trained to predict user goals and to generate contextually relevant chit-chat responses. Automatic and human evaluations show that, compared with the state-of-the-art task-oriented baseline, our models can code-switch between task and chit-chat to be more engaging, interesting, knowledgeable, and humanlike, while maintaining competitive task performance.

pdf bib
Recipes for Building an Open-Domain Chatbot
Stephen Roller | Emily Dinan | Naman Goyal | Da Ju | Mary Williamson | Yinhan Liu | Jing Xu | Myle Ott | Eric Michael Smith | Y-Lan Boureau | Jason Weston
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we highlight other ingredients. Good conversation requires blended skills: providing engaging talking points, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.


pdf bib
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
Kurt Shuster | Da Ju | Stephen Roller | Emily Dinan | Y-Lan Boureau | Jason Weston
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations, and perceive and converse about images. By multi-tasking on such a broad large-scale set of data, we hope to both move towards and measure progress in producing a single unified agent that can perceive, reason and converse with humans in an open-domain setting. We show that such multi-tasking improves over a BERT pre-trained baseline, largely due to multi-tasking with very large dialogue datasets in a similar domain, and that the multi-tasking in general provides gains to both text and image-based tasks using several metrics in both the fine-tune and task transfer settings. We obtain state-of-the-art results on many of the tasks, providing a strong baseline for this challenge.

pdf bib
Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Margaret Li | Stephen Roller | Ilia Kulikov | Sean Welleck | Y-Lan Boureau | Kyunghyun Cho | Jason Weston
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within utterances, (iii) overuse frequent words, and (iv) at a deeper level, contain logical flaws.In this work we show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019) to these cases. We show that appropriate loss functions which regularize generated outputs to match human distributions are effective for the first three issues. For the last important general issue, we show applying unlikelihood to collected data of what a model should not do is effective for improving logical consistency, potentially paving the way to generative models with greater reasoning ability. We demonstrate the efficacy of our approach across several dialogue tasks.


pdf bib
What makes a good conversation? How controllable attributes affect human judgments
Abigail See | Stephen Roller | Douwe Kiela | Jason Weston
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

A good conversation requires balance – between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly evaluated via human judgments of overall quality, the relationship between quality and these individual factors is less well-studied. In this work, we examine two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chit-chat dialogue: repetition, specificity, response-relatedness and question-asking. We conduct a large-scale human evaluation to measure the effect of these control parameters on multi-turn interactive conversations on the PersonaChat task. We provide a detailed analysis of their relationship to high-level aspects of conversation, and show that by controlling combinations of these variables our models obtain clear improvements in human quality judgments.

pdf bib
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
Matthew Le | Stephen Roller | Laetitia Papaxanthos | Douwe Kiela | Maximilian Nickel
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We consider the task of inferring “is-a” relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate constraints for inferring concept hierarchies from distributional contexts while also being able to predict missing “is-a”-relationships and to correct wrong extractions. Moreover – and in contrast with other methods – the hierarchical nature of hyperbolic space allows us to learn highly efficient representations and to improve the taxonomic consistency of the inferred hierarchies. Experimentally, we show that our approach achieves state-of-the-art performance on several commonly-used benchmarks.


pdf bib
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
Stephen Roller | Douwe Kiela | Maximilian Nickel
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Methods for unsupervised hypernym detection may broadly be categorized according to two paradigms: pattern-based and distributional methods. In this paper, we study the performance of both approaches on several hypernymy tasks and find that simple pattern-based methods consistently outperform distributional methods on common benchmark datasets. Our results show that pattern-based models provide important contextual constraints which are not yet captured in distributional methods.


pdf bib
Distributional Modeling on a Diet: One-shot Word Learning from Text Only
Su Wang | Stephen Roller | Katrin Erk
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative.


pdf bib
Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment
Stephen Roller | Katrin Erk
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
PIC a Different Word: A Simple Model for Lexical Substitution in Context
Stephen Roller | Katrin Erk
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
Ye Zhang | Stephen Roller | Byron C. Wallace
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Representing Meaning with a Combination of Logical and Distributional Models
I. Beltagy | Stephen Roller | Pengxiang Cheng | Katrin Erk | Raymond J. Mooney
Computational Linguistics, Volume 42, Issue 4 - December 2016


pdf bib
Feature Norms of German Noun Compounds
Stephen Roller | Sabine Schulte im Walde
Proceedings of the 10th Workshop on Multiword Expressions (MWE)

pdf bib
UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic
Islam Beltagy | Stephen Roller | Gemma Boleda | Katrin Erk | Raymond Mooney
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

pdf bib
Inclusive yet Selective: Supervised Distributional Hypernymy Detection
Stephen Roller | Katrin Erk | Gemma Boleda
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers


pdf bib
A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities
Stephen Roller | Sabine Schulte im Walde
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
The (Un)expected Effects of Applying Standard Cleansing Models to Human Ratings on Compositionality
Stephen Roller | Sabine Schulte im Walde | Silke Scheible
Proceedings of the 9th Workshop on Multiword Expressions


pdf bib
Supervised Text-based Geolocation Using Language Models on an Adaptive Grid
Stephen Roller | Michael Speriosu | Sarat Rallapalli | Benjamin Wing | Jason Baldridge
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning