Search Results for author:
Found 56 papers, 7 papers with code
Adaptor Grammars for Unsupervised Paradigm Clustering
This work describes the Edinburgh submission to the SIGMORPHON 2021 Shared Task 2 on unsupervised morphological paradigm clustering.
Conditioning, but on Which Distribution? Grammatical Gender in German Plural Inflection
Grammatical gender is a consistent and informative cue to the plural class of German nouns.
LLMs Reproduce Stereotypes of Sexual and Gender Minorities
A large body of research has found substantial gender bias in NLP systems.
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs).
Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification
We then show that they can be prevented in practice by introducing a Discrete Fourier Transform (DFT) output layer, which guarantees that all sparse label combinations with up to $k$ active labels are argmaxable.
Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
We also find racial biases to be much more prevalent than gender biases.
Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages
To remedy this, we build a counterfactual evaluation corpus for gender and racial/migrant bias in four languages.
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice
Classifiers in natural language processing (NLP) often have a large number of output classes.
SemEval 2021 Task 7: HaHackathon, Detecting and Rating Humor and Offense
Our subtasks were binary humor detection, prediction of humor and offense ratings, and a novel controversy task: to predict if the variance in the humor ratings was higher than a specific threshold.
Intrinsic Bias Metrics Do Not Correlate with Application Bias
We urge researchers working on debiasing to focus on extrinsic measures of bias, and to make using these measures more feasible via creation of new challenge sets and annotated test data.
LSTMs Compose---and Learn---Bottom-Up
To explore the inductive biases that cause these compositional representations to arise during training, we conduct simple experiments on synthetic data.
LemMED: Fast and Effective Neural Morphological Analysis with Short Context Windows
We present LemMED, a character-level encoder-decoder for contextual morphological analysis (combined lemmatization and tagging).
LSTMs Compose (and Learn) Bottom-Up
To explore the inductive biases that cause these compositional representations to arise during training, we conduct simple experiments on synthetic data.
Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals
Encoder-decoder models do generalize the most frequently produced plural class, but do not show human-like variability or 'regular' extension of these other plural markers.
Word Interdependence Exposes How LSTMs Compose Representations
Recent work in NLP shows that LSTM language models capture compositional structure in language data.
How to Evaluate Word Representations of Informal Domain?
Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications.
Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction.
Ranked #5 on
DRS Parsing
on PMB-2.2.0
A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Parsers are available for only a handful of the world's languages, since they require lots of training data.
Cross-lingual topic prediction for speech using translations
Given a large amount of unannotated speech in a low-resource language, can we classify the speech utterances by topic?
Sparsity Emerges Naturally in Neural Language Models
Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks.
Do LSTMs Learn Compositionally?
LSTM-based language models exhibit compositionality in their representations, but how this behavior emerges over the course of training has not been explored.
Understanding Learning Dynamics Of Language Models with SVCCA
Research has shown that neural models implicitly encode linguistic features, but there has been no research showing \emph{how} these encodings arise as the models are trained.
`Indicatements' that character language models learn English morpho-syntactic units and regularities
Character language models have access to surface morphological patterns, but it is not clear whether or \textit{how} they learn abstract morphological regularities.
Explicitly modeling case improves neural dependency parsing
Neural dependency parsing models that compose word representations from characters can presumably exploit morphosyntax when making attachment decisions.
Language Models Learn POS First
A glut of recent research shows that language models capture linguistic structure.
The problem with probabilistic DAG automata for semantic graphs
Semantic representations in the form of directed acyclic graphs (DAGs) have been introduced in recent years, and to model them, we need probabilistic models of DAGs.
Neural Networks for Cross-lingual Negation Scope Detection
Negation scope has been annotated in several English and Chinese corpora, and highly accurate models for this task in these languages have been learned from these annotations.
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation
Finally, we show that the approach improves performance on a true low-resource task: pre-training on a combination of English ASR and French ASR improves Mboshi-French ST, where only 4 hours of data are available, from 3. 5 to 7. 1
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Indicatements that character language models learn English morpho-syntactic units and regularities
Character language models have access to surface morphological patterns, but it is not clear whether or how they learn abstract morphological regularities.
What do character-level models learn about morphology? The case of dependency parsing
When parsing morphologically-rich languages with neural models, it is beneficial to model input at the character level, and it has been claimed that this is because character-level models learn morphology.
Does Ability Affect Alignment in Second Language Tutorial Dialogue?
We find that lexical priming in learner-tutor dialogues differs from that in conversational and task-based dialogues, and we find evidence that alignment increases with ability and with word complexity.
A Structured Syntax-Semantics Interface for English-AMR Alignment
Abstract Meaning Representation (AMR) annotations are often assumed to closely mirror dependency syntax, but AMR explicitly does not require this, and the assumption has never been tested.
Low-Resource Speech-to-Text Translation
We explore models trained on between 20 and 160 hours of data, and find that although models trained on less data have considerably lower BLEU scores, they can still predict words with relatively high precision and recall---around 50% for a model trained on 50 hours of data, versus around 60% for the full 160 hour model.
Weighted DAG Automata for Semantic Graphs
Graphs have a variety of uses in natural language processing, particularly as representations of linguistic meaning.
Spoken Term Discovery for Language Documentation using Translations
Vast amounts of speech data collected for language documentation and research remain untranscribed and unsearchable, but often a small amount of speech may have text translations available.
A Generative Parser with a Discriminative Recognition Algorithm
Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models.
Parsing Graphs with Regular Graph Grammars
Recently, several datasets have become available which represent natural language phenomena as graphs.
UParse: the Edinburgh system for the CoNLL 2017 UD shared task
This paper presents our submissions for the CoNLL 2017 UD Shared Task.
From Characters to Words to in Between: Do We Capture Morphology?
Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams.
Detecting negation scope is easy, except when it isn't
Several corpora have been annotated with negation scope{---}the set of words whose meaning is negated by a cue like the word {``}not{''}{---}leading to the development of classifiers that detect negation scope with high accuracy.
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.
Towards speech-to-text translation without speech recognition
We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
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.
Weakly supervised spoken term discovery using cross-lingual side information
Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone.
Evaluating Informal-Domain Word Representations With UrbanDictionary
Existing corpora for intrinsic evaluation are not targeted towards tasks in informal domains such as Twitter or news comment forums.
Gappy Pattern Matching on GPUs for On-Demand Extraction of Hierarchical Translation Grammars
We believe that GPU-based extraction of hierarchical grammars is an attractive proposition, particularly for MT applications that demand high throughput.
Learning to translate with products of novices: a suite of open-ended challenge problems for teaching MT
Machine translation (MT) draws from several different disciplines, making it a complex subject to teach.
