Search Results for author:
Found 35 papers, 5 papers with code
Learning from Limited Labels for Long Legal Dialogue
We study four representative tasks from the parole dataset.
Large-Scale Quantitative Evaluation of Dialogue Agents’ Response Strategies against Offensive Users
As voice assistants and dialogue agents grow in popularity, so does the abuse they receive.
Effective Social Chatbot Strategies for Increasing User Initiative
Many existing chatbots do not effectively support mixed initiative, forcing their users to either respond passively or lead constantly.
Understanding and predicting user dissatisfaction in a neural generative chatbot
We find that unclear user utterances are a major source of generative errors such as ignoring, hallucination, unclearness and repetition.
Challenges for Information Extraction from Dialogue in Criminal Law
Information extraction and question answering have the potential to introduce a new paradigm for how machine learning is applied to criminal law.
Do "English" Named Entity Recognizers Work Well on Global Englishes?
We test widely used NER toolkits and transformer models, including models using the pre-trained contextual models RoBERTa and ELECTRA, on three datasets: a commonly used British English newswire dataset, CoNLL 2003, a more American focused dataset OntoNotes, and our global dataset.
FLawN-T5: An Empirical Examination of Effective Instruction-Tuning Data Mixtures for Legal Reasoning
In this work, we curate LawInstruct, a large legal instruction dataset, covering 17 jurisdictions, 24 languages and a total of 12M examples.
BAGEL: Bootstrapping Agents by Guiding Exploration with Language
Unfortunately, LM agents often fail to generalize to new environments without human demonstrations.
Machine Translation for Nko: Tools, Corpora and Baseline Results
Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value.
JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset
While our work, along with previous work, shows that transfer from these models to low-resource languages that are unrelated to languages in their training set is not very effective, we would expect stronger results from transfer to creoles.
DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference
Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training.
Towards Ecologically Valid Research on Language User Interfaces
To this end, we describe what we deem an ideal methodology for machine learning research on LUIs and categorize five common ways in which recent benchmarks deviate from it.
Robust Subgraph Generation Improves Abstract Meaning Representation Parsing
The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation.
GloVe: Global Vectors for Word Representation
Ranked #14 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
Event Extraction Using Distant Supervision
We present a new publicly available dataset and event extraction task in the plane crash domain based on Wikipedia infoboxes and newswire text.
SUTime: A library for recognizing and normalizing time expressions
We describe SUTIME, a temporal tagger for recognizing and normalizing temporal expressions in English text.
Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency
We present a generative model for the unsupervised learning of dependency structures.
Ranked #5 on
Unsupervised Dependency Parsing
on Penn Treebank
