Search Results for author:
Found 62 papers, 37 papers with code
Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions
Our model outperforms the state-of-the-art NMN model on CLEVR-Ref+ dataset with +8. 1% improvement in accuracy on the single-referent test set and +4. 3% on the full test set.
In-Context Learning for Text Classification with Many Labels
We analyze the performance across number of in-context examples and different model scales, showing that larger models are necessary to effectively and consistently make use of larger context lengths for ICL.
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Guided by human evaluation and analysis, we highlight the shortcomings of traditional metrics for both correctness and faithfulness.
The Impact of Positional Encoding on Length Generalization in Transformers
In this paper, we conduct a systematic empirical study comparing the length generalization performance of decoder-only Transformers with five different position encoding approaches including Absolute Position Embedding (APE), T5's Relative PE, ALiBi, and Rotary, in addition to Transformers without positional encoding (NoPE).
Are Diffusion Models Vision-And-Language Reasoners?
We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2. 1 is, for the most part, less biased than Stable Diffusion 1. 5.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
We introduce the StatCan Dialogue Dataset consisting of 19, 379 conversation turns between agents working at Statistics Canada and online users looking for published data tables.
Ranked #1 on
Table Retrieval
on Statcan Dialogue Dataset
Using In-Context Learning to Improve Dialogue Safety
For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.
Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model
Augmenting pretrained language models with retrievers to select the supporting documents has shown promise in effectively solving common NLP problems, including language modeling and question answering, in an interpretable way.
Syntactic Substitutability as Unsupervised Dependency Syntax
Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language.
The Curious Case of Absolute Position Embeddings
Transformer language models encode the notion of word order using positional information.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems
Our personalized feedback can pinpoint correct and incorrect or missing phrases in student answers as well as guide them towards correct answer by asking a question in natural language.
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue
The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources.
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination.
Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment
We train a neural model with this feedback data that can generate explanations and re-score answer candidates.
Ranked #1 on
Overall - Test
on FeedbackQA
Image Retrieval from Contextual Descriptions
In particular, models are tasked with retrieving the correct image from a set of 10 minimally contrastive candidates based on a contextual description.
Ranked #1 on
Image Retrieval
on ImageCoDe
Combining Modular Skills in Multitask Learning
By jointly learning these and a task-skill allocation matrix, the network for each task is instantiated as the average of the parameters of active skills.
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
Our benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups.
Does Entity Abstraction Help Generative Transformers Reason?
We study the utility of incorporating entity type abstractions into pre-trained Transformers and test these methods on four NLP tasks requiring different forms of logical reasoning: (1) compositional language understanding with text-based relational reasoning (CLUTRR), (2) abductive reasoning (ProofWriter), (3) multi-hop question answering (HotpotQA), and (4) conversational question answering (CoQA).
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on.
The Power of Prompt Tuning for Low-Resource Semantic Parsing
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and generation tasks.
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
The principle is that this should result in worse model performance compared to masking random tokens.
Compositional Generalization in Dependency Parsing
To test compositional generalization in semantic parsing, Keysers et al. (2020) introduced Compositional Freebase Queries (CFQ).
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents).
Visually Grounded Reasoning across Languages and Cultures
The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and images of ImageNet.
Ranked #1 on
Zero-Shot Cross-Lingual Transfer
on MaRVL
Post-hoc Interpretability for Neural NLP: A Survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use.
Modelling Latent Translations for Cross-Lingual Transfer
To remedy this, we propose a new technique that integrates both steps of the traditional pipeline (translation and classification) into a single model, by treating the intermediate translations as a latent random variable.
Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering
We introduce Abg-CoQA, a novel dataset for clarifying ambiguity in Conversational Question Answering systems.
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
We model retrieval decisions as latent variables over sets of relevant documents.
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
In fact, under a decision-theoretic framework, MAML can be interpreted as minimising the expected risk across training languages (with a uniform prior), which is known as Bayes criterion.
Understanding by Understanding Not: Modeling Negation in Language Models
To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus.
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
We run UDA experiments on question generation and passage retrieval from the \textit{Natural Questions} domain to machine learning and biomedical domains.
MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining
One of the biggest challenges that prohibit the use of many current NLP methods in clinical settings is the availability of public datasets.
Ranked #1 on
Mortality Prediction
on MIMIC-III
(Accuracy metric)
Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM).
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback
The ubiquitous nature of chatbots and their interaction with users generate an enormous amount of data.
Measuring Systematic Generalization in Neural Proof Generation with Transformers
We observe that models that are not trained to generate proofs are better at generalizing to problems based on longer proofs.
Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions
To measure the true progress of existing models, we split the test set into two sets, one which requires reasoning on linguistic structure and the other which doesn't.
StereoSet: Measuring stereotypical bias in pretrained language models
Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases.
Ranked #1 on
Bias Detection
on StereoSet
Building a Neural Semantic Parser from a Domain Ontology
We address these challenges with a framework which allows to elicit training data from a domain ontology and bootstrap a neural parser which recursively builds derivations of logical forms.
CoQA: A Conversational Question Answering Challenge
Humans gather information by engaging in conversations involving a series of interconnected questions and answers.
Ranked #3 on
Generative Question Answering
on CoQA
Conversational Question Answering
Generative Question Answering
+1
Learning Typed Entailment Graphs with Global Soft Constraints
We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph.
Learning an Executable Neural Semantic Parser
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response.
Learning to Paraphrase for Question Answering
Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need.
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.
Learning Structured Natural Language Representations for Semantic Parsing
We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains.
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks
Existing question answering methods infer answers either from a knowledge base or from raw text.
Universal Dependencies to Logical Form with Negation Scope
Many language technology applications would benefit from the ability to represent negation and its scope on top of widely-used linguistic resources.
Universal Dependencies to Logical Forms with Negation Scope
Many language technology applications would benefit from the ability to represent negation and its scope on top of widely-used linguistic resources.
Universal Semantic Parsing
In this work, we introduce UDepLambda, a semantic interface for UD, which maps natural language to logical forms in an almost language-independent fashion and can process dependency graphs.
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Our results on WMT data show that explicitly modeling target-syntax improves machine translation quality for German->English, a high-resource pair, and for Romanian->English, a low-resource pair and also several syntactic phenomena including prepositional phrase attachment.
Evaluating Induced CCG Parsers on Grounded Semantic Parsing
We compare the effectiveness of four different syntactic CCG parsers for a semantic slot-filling task to explore how much syntactic supervision is required for downstream semantic analysis.
DNN-based Speech Synthesis for Indian Languages from ASCII text
These methods first convert the ASCII text to a phonetic script, and then learn a Deep Neural Network to synthesize speech from that.
Question Answering on Freebase via Relation Extraction and Textual Evidence
Existing knowledge-based question answering systems often rely on small annotated training data.
Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing
One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries -- there are many ways to ask a question, all with the same answer.
Transforming Dependency Structures to Logical Forms for Semantic Parsing
In contrast{---}partly due to the lack of a strong type system{---}dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages.
Large-scale Semantic Parsing without Question-Answer Pairs
In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs.
Word Sketches for Turkish
Word sketches are one-page, automatic, corpus-based summaries of a word's grammatical and collocational behaviour.
