17 citations · 46 across the 16 of their papers we have counts for
21 papers
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice
Andreas Grivas, Nikolay Bogoychev, Adam Lopez
Classifiers in natural language processing (NLP) often have a large number of output classes. For example, neural language models (LMs) and machine translation (MT) models both pre…
Intrinsic Bias Metrics Do Not Correlate with Application Bias
Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sanchez +2
Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at…
LemMED: Fast and Effective Neural Morphological Analysis with Short Context Windows
Aibek Makazhanov, Sharon Goldwater, Adam Lopez
We present LemMED, a character-level encoder-decoder for contextual morphological analysis (combined lemmatization and tagging). LemMED extends and is named after two other attenti…
LSTMs Compose (and Learn) Bottom-Up
Naomi Saphra, Adam Lopez
Recent work in NLP shows that LSTM language models capture hierarchical structure in language data. In contrast to existing work, we consider the \textit{learning} process that lea…
Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals
Kate McCurdy, Sharon Goldwater, Adam Lopez
Can artificial neural networks learn to represent inflectional morphology and generalize to new words as human speakers do? Kirov and Cotterell (2018) argue that the answer is yes:…
Word Interdependence Exposes How LSTMs Compose Representations
Naomi Saphra, Adam Lopez
Recent work in NLP shows that LSTM language models capture compositional structure in language data. For a closer look at how these representations are composed hierarchically, we…
How to Evaluate Word Representations of Informal Domain?
Yekun Chai, Naomi Saphra, Adam Lopez
Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications. Nevertheless, how to efficiently evaluate such word embeddings in…
Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
Federico Fancellu, Sorcha Gilroy, Adam Lopez +1
Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it…
Cross-lingual topic prediction for speech using translations
Sameer Bansal, Herman Kamper, Adam Lopez +1
Given a large amount of unannotated speech in a low-resource language, can we classify the speech utterances by topic? We consider this question in the setting where a small amount…
Sparsity Emerges Naturally in Neural Language Models
Naomi Saphra, Adam Lopez
Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks. If sparsity is impo…
Neural Networks for Cross-lingual Negation Scope Detection
Federico Fancellu, Adam Lopez, Bonnie Webber
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. Unfo…
The problem with probabilistic DAG automata for semantic graphs
Ieva Vasiljeva, Sorcha Gilroy, Adam Lopez
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. One model that…
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation
Sameer Bansal, Herman Kamper, Karen Livescu +2
We present a simple approach to improve direct speech-to-text translation (ST) when the source language is low-resource: we pre-train the model on a high-resource automatic speech…
Indicatements that character language models learn English morpho-syntactic units and regularities
Yova Kementchedjhieva, Adam Lopez
Character language models have access to surface morphological patterns, but it is not clear whether or how they learn abstract morphological regularities. We instrument a characte…
What do character-level models learn about morphology? The case of dependency parsing
Clara Vania, Andreas Grivas, Adam Lopez
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…
Low-Resource Speech-to-Text Translation
Sameer Bansal, Herman Kamper, Karen Livescu +2
Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often im…
A Generative Parser with a Discriminative Recognition Algorithm
Jianpeng Cheng, Adam Lopez, Mirella Lapata
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…
From Characters to Words to in Between: Do We Capture Morphology?
Clara Vania, Adam Lopez
Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and…
Towards speech-to-text translation without speech recognition
Sameer Bansal, Herman Kamper, Adam Lopez +1
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 h…
Universal Dependencies to Logical Forms with Negation Scope
Federico Fancellu, Siva Reddy, Adam Lopez +1
Many language technology applications would benefit from the ability to represent negation and its scope on top of widely-used linguistic resources. In this paper, we investigate t…
Weakly supervised spoken term discovery using cross-lingual side information
Sameer Bansal, Herman Kamper, Sharon Goldwater +1
Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone. These systems are promising for some very low-resource lang…