2021
pdf
bib
abs
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
Sonia Raychaudhuri
|
Saim Wani
|
Shivansh Patel
|
Unnat Jain
|
Angel Chang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle ‘off the path’ scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent’s location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we propose a simple and effective language-aligned supervision scheme, and a new metric that measures the number of sub-instructions the agent has completed during navigation.
2019
pdf
bib
abs
Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue
Justin Dieter
|
Tian Wang
|
Arun Tejasvi Chaganty
|
Gabor Angeli
|
Angel X. Chang
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
Reflective listening–demonstrating that you have heard your conversational partner–is key to effective communication. Expert human communicators often mimic and rephrase their conversational partner, e.g., when responding to sentimental stories or to questions they don’t know the answer to. We introduce a new task and an associated dataset wherein dialogue agents similarly mimic and rephrase a user’s request to communicate sympathy (I’m sorry to hear that) or lack of knowledge (I do not know that). We study what makes a rephrasal response good against a set of qualitative metrics. We then evaluate three models for generating responses: a syntax-aware rule-based system, a seq2seq LSTM neural models with attention (S2SA), and the same neural model augmented with a copy mechanism (S2SA+C). In a human evaluation, we find that S2SA+C and the rule-based system are comparable and approach human-generated response quality. In addition, experiences with a live deployment of S2SA+C in a customer support setting suggest that this generation task is a practical contribution to real world conversational agents.
2017
pdf
bib
abs
A Two-stage Sieve Approach for Quote Attribution
Grace Muzny
|
Michael Fang
|
Angel Chang
|
Dan Jurafsky
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
We present a deterministic sieve-based system for attributing quotations in literary text and a new dataset: QuoteLi3. Quote attribution, determining who said what in a given text, is important for tasks like creating dialogue systems, and in newer areas like computational literary studies, where it creates opportunities to analyze novels at scale rather than only a few at a time. We release QuoteLi3, which contains more than 6,000 annotations linking quotes to speaker mentions and quotes to speaker entities, and introduce a new algorithm for quote attribution. Our two-stage algorithm first links quotes to mentions, then mentions to entities. Using two stages encapsulates difficult sub-problems and improves system performance. The modular design allows us to tune for overall performance or higher precision, which is useful for many real-world use cases. Our system achieves an average F-score of 87.5 across three novels, outperforming previous systems, and can be tuned for precision of 90.4 at a recall of 65.1.
2016
pdf
bib
abs
A comparison of Named-Entity Disambiguation and Word Sense Disambiguation
Angel Chang
|
Valentin I. Spitkovsky
|
Christopher D. Manning
|
Eneko Agirre
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia-derived resources like DBpedia. This task is closely related to word-sense disambiguation (WSD), where the mention of an open-class word is linked to a concept in a knowledge-base, typically WordNet. This paper analyzes the relation between two annotated datasets on NED and WSD, highlighting the commonalities and differences. We detail the methods to construct a NED system following the WSD word-expert approach, where we need a dictionary and one classifier is built for each target entity mention string. Constructing a dictionary for NED proved challenging, and although similarity and ambiguity are higher for NED, the results are also higher due to the larger number of training data, and the more crisp and skewed meaning differences.
2015
pdf
bib
Text to 3D Scene Generation with Rich Lexical Grounding
Angel Chang
|
Will Monroe
|
Manolis Savva
|
Christopher Potts
|
Christopher D. Manning
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
pdf
bib
Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval
Sebastian Schuster
|
Ranjay Krishna
|
Angel Chang
|
Li Fei-Fei
|
Christopher D. Manning
Proceedings of the Fourth Workshop on Vision and Language
2014
pdf
bib
Semantic Parsing for Text to 3D Scene Generation
Angel Chang
|
Manolis Savva
|
Christopher Manning
Proceedings of the ACL 2014 Workshop on Semantic Parsing
pdf
bib
Interactive Learning of Spatial Knowledge for Text to 3D Scene Generation
Angel Chang
|
Manolis Savva
|
Christopher Manning
Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces
pdf
bib
Learning Spatial Knowledge for Text to 3D Scene Generation
Angel Chang
|
Manolis Savva
|
Christopher D. Manning
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
2013
pdf
bib
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules
Heeyoung Lee
|
Angel Chang
|
Yves Peirsman
|
Nathanael Chambers
|
Mihai Surdeanu
|
Dan Jurafsky
Computational Linguistics, Volume 39, Issue 4 - December 2013
pdf
bib
SUTime: Evaluation in TempEval-3
Angel Chang
|
Christopher D. Manning
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)
2012
pdf
bib
Joint Entity and Event Coreference Resolution across Documents
Heeyoung Lee
|
Marta Recasens
|
Angel Chang
|
Mihai Surdeanu
|
Dan Jurafsky
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
pdf
bib
abs
A Cross-Lingual Dictionary for English Wikipedia Concepts
Valentin I. Spitkovsky
|
Angel X. Chang
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
We present a resource for automatically associating strings of text with English Wikipedia concepts. Our machinery is bi-directional, in the sense that it uses the same fundamental probabilistic methods to map strings to empirical distributions over Wikipedia articles as it does to map article URLs to distributions over short, language-independent strings of natural language text. For maximal inter-operability, we release our resource as a set of flat line-based text files, lexicographically sorted and encoded with UTF-8. These files capture joint probability distributions underlying concepts (we use the terms article, concept and Wikipedia URL interchangeably) and associated snippets of text, as well as other features that can come in handy when working with Wikipedia articles and related information.
pdf
bib
abs
SUTime: A library for recognizing and normalizing time expressions
Angel X. Chang
|
Christopher Manning
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
We describe SUTIME, a temporal tagger for recognizing and normalizing temporal expressions in English text. SUTIME is available as part of the Stanford CoreNLP pipeline and can be used to annotate documents with temporal information. It is a deterministic rule-based system designed for extensibility. Testing on the TempEval-2 evaluation corpus shows that this system outperforms state-of-the-art techniques.
2011
pdf
bib
Unsupervised Dependency Parsing without Gold Part-of-Speech Tags
Valentin I. Spitkovsky
|
Hiyan Alshawi
|
Angel X. Chang
|
Daniel Jurafsky
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing
pdf
bib
Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
Heeyoung Lee
|
Yves Peirsman
|
Angel Chang
|
Nathanael Chambers
|
Mihai Surdeanu
|
Dan Jurafsky
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task