343 citations · 894 across the 51 of their papers we have counts for
64 papers
A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents
Sukai Huang, Nir Lipovetzky, Trevor Cohn
Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Wit…
The Next Chapter: A Study of Large Language Models in Storytelling
Zhuohan Xie, Trevor Cohn, Jey Han Lau
To enhance the quality of generated stories, recent story generation models have been investigating the utilization of higher-level attributes like plots or commonsense knowledge.…
A Survey for Efficient Open Domain Question Answering
Qin Zhang, Shangsi Chen, Dongkuan Xu +4
Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language pr…
Rethinking Round-Trip Translation for Machine Translation Evaluation
Terry Yue Zhuo, Qiongkai Xu, Xuanli He +1
Automatic evaluation on low-resource language translation suffers from a deficiency of parallel corpora. Round-trip translation could be served as a clever and straightforward tech…
Incorporating Constituent Syntax for Coreference Resolution
Fan Jiang, Trevor Cohn
Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statis…
Exploring Story Generation with Multi-task Objectives in Variational Autoencoders
Zhuohan Xie, Trevor Cohn, Jey Han Lau
GPT-2 has been frequently adapted in story generation models as it provides powerful generative capability. However, it still fails to generate consistent stories and lacks diversi…
It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
Jinming Zhao, Philip Arthur, Gholamreza Haffari +2
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on r…
Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data
Kemal Kurniawan, Lea Frermann, Philip Schulz +1
Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalis…
Contrastive Learning for Fair Representations
Aili Shen, Xudong Han, Trevor Cohn +2
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing me…
Fairness-aware Class Imbalanced Learning
Shivashankar Subramanian, Afshin Rahimi, Timothy Baldwin +2
Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the…
Evaluating Debiasing Techniques for Intersectional Biases
Shivashankar Subramanian, Xudong Han, Timothy Baldwin +2
Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in…
Commonsense Knowledge in Word Associations and ConceptNet
Chunhua Liu, Trevor Cohn, Lea Frermann
Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, unders…
Generating Diverse Descriptions from Semantic Graphs
Jiuzhou Han, Daniel Beck, Trevor Cohn
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation proble…
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Jun Wang, Chang Xu, Francisco Guzman +3
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robust…
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Jun Wang, Chang Xu, Francisco Guzman +4
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.…
Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames
Shima Khanehzar, Trevor Cohn, Gosia Mikolajczak +2
Understanding how news media frame political issues is important due to its impact on public attitudes, yet hard to automate. Computational approaches have largely focused on class…
Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics
Nitika Mathur, Timothy Baldwin, Trevor Cohn
Automatic metrics are fundamental for the development and evaluation of machine translation systems. Judging whether, and to what extent, automatic metrics concur with the gold sta…
Grounding learning of modifier dynamics: An application to color naming
Xudong Han, Philip Schulz, Trevor Cohn
Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as 'dirty blue'. We present a model of color modifie…
Deep Ordinal Regression for Pledge Specificity Prediction
Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin
Many pledges are made in the course of an election campaign, forming important corpora for political analysis of campaign strategy and governmental accountability. At present, ther…
Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings
Zenan Zhai, Dat Quoc Nguyen, Saber A. Akhondi +5
Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in pa…
Semi-supervised Stochastic Multi-Domain Learning using Variational Inference
Yitong Li, Timothy Baldwin, Trevor Cohn
Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient qua…
Target Based Speech Act Classification in Political Campaign Text
Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin
We study pragmatics in political campaign text, through analysis of speech acts and the target of each utterance. We propose a new annotation schema incorporating domain-specific s…
Contextualization of Morphological Inflection
Ekaterina Vylomova, Ryan Cotterell, Timothy Baldwin +2
Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partiall…
A Unified Neural Architecture for Instrumental Audio Tasks
Steven Spratley, Daniel Beck, Trevor Cohn
Within Music Information Retrieval (MIR), prominent tasks -- including pitch-tracking, source-separation, super-resolution, and synthesis -- typically call for specialised methods,…