Search Results for author:
Found 79 papers, 16 papers with code
Evaluating Gender Bias Transfer from Film Data
We extend our analysis to a longitudinal study of bias in film dialogue over the last 110 years and find that continued pre-training on OpenSubtitles encodes additional bias into BERT.
LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification
In this paper we describe our submission for the task of Propaganda Span Identification in news articles.
Nonlinear ISA with Auxiliary Variables for Learning Speech Representations
This paper extends recent work on nonlinear Independent Component Analysis (ICA) by introducing a theoretical framework for nonlinear Independent Subspace Analysis (ISA) in the presence of auxiliary variables.
Should You Fine-Tune BERT for Automated Essay Scoring?
Most natural language processing research now recommends large Transformer-based models with fine-tuning for supervised classification tasks; older strategies like bag-of-words features and linear models have fallen out of favor.
ClarQ: A large-scale and diverse dataset for Clarification Question Generation
In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange.
A Corpus for Large-Scale Phonetic Typology
A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions.
Phone Features Improve Speech Translation
End-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate ASR and MT models, with simpler model architectures and the potential for reduced error propagation.
Exploring Controllable Text Generation Techniques
In this work, we provide a new schema of the pipeline of the generation process by classifying it into five modules.
Style Variation as a Vantage Point for Code-Switching
We believe this viewpoint of CS as style variations opens new perspectives for modeling various tasks in CS text.
Topological Sort for Sentence Ordering
Sentence ordering is the task of arranging the sentences of a given text in the correct order.
Politeness Transfer: A Tag and Generate Approach
This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning.
AlloVera: A Multilingual Allophone Database
While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription.
Towards Zero-shot Learning for Automatic Phonemic Transcription
The difficulty of this task is that phoneme inventories often differ between the training languages and the target language, making it infeasible to recognize unseen phonemes.
Universal Phone Recognition with a Multilingual Allophone System
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages.
Towards Minimal Supervision BERT-based Grammar Error Correction
Current grammatical error correction (GEC) models typically consider the task as sequence generation, which requires large amounts of annotated data and limit the applications in data-limited settings.
A Resource for Computational Experiments on Mapudungun
We present a resource for computational experiments on Mapudungun, a polysynthetic indigenous language spoken in Chile with upwards of 200 thousand speakers.
Question Answering for Privacy Policies: Combining Computational and Legal Perspectives
The PrivacyQA corpus offers a challenging corpus for question answering, with genuine real-world utility.
Multimodal, Multilingual Grapheme-to-Phoneme Conversion for Low-Resource Languages
Grapheme-to-phoneme conversion (g2p) is the task of predicting the pronunciation of words from their orthographic representation.
What A Sunny Day ☔: Toward Emoji-Sensitive Irony Detection
Irony detection is an important task with applications in identification of online abuse and harassment.
Formality Style Transfer for Noisy, User-generated Conversations: Extracting Labeled, Parallel Data from Unlabeled Corpora
Typical datasets used for style transfer in NLP contain aligned pairs of two opposite extremes of a style.
Learning to Order Graph Elements with Application to Multilingual Surface Realization
Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences.
A Dynamic Strategy Coach for Effective Negotiation
We consider a bargaining scenario where a seller and a buyer negotiate the price of an item for sale through a text-based dialog.
Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History
We train FSTs on a set of strategies and tactics used in negotiation dialogs.
Induction and Reference of Entities in a Visual Story
We also conduct human evaluation from which it is concluded that the visual stories generated by our model are preferred 82% of the times.
CMU GetGoing: An Understandable and Memorable Dialog System for Seniors
Voice-based technologies are typically developed for the average user, and thus generally not tailored to the specific needs of any subgroup of the population, like seniors.
Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs
In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e. g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves.
Multilingual Speech Recognition with Corpus Relatedness Sampling
For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language.
SANTLR: Speech Annotation Toolkit for Low Resource Languages
In this work, we present SANTLR: Speech Annotation Toolkit for Low Resource Languages.
Equity Beyond Bias in Language Technologies for Education
There is a long record of research on equity in schools.
``My Way of Telling a Story'': Persona based Grounded Story Generation
To this end, we propose five models which are incremental extensions to the baseline model to perform the task at hand.
WriterForcing: Generating more interesting story endings
In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generation of non-generic words.
Boosting Dialog Response Generation
Neural models have become one of the most important approaches to dialog response generation.
Storyboarding of Recipes: Grounded Contextual Generation
We introduce a dataset for sequential procedural (how-to) text generation from images in cooking domain.
Measuring Bias in Contextualized Word Representations
Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks.
Principled Frameworks for Evaluating Ethics in NLP Systems
We critique recent work on ethics in natural language processing.
"My Way of Telling a Story": Persona based Grounded Story Generation
To this end, we propose five models which are incremental extensions to the baseline model to perform the task at hand.
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation
Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text.
Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar
We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner.
The Zero Resource Speech Challenge 2019: TTS without T
We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text).
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings
Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways.
A Survey of Code-switched Speech and Language Processing
Code-switching, the alternation of languages within a conversation or utterance, is a common communicative phenomenon that occurs in multilingual communities across the world.
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
Phoneme Level Language Models for Sequence Based Low Resource ASR
Building multilingual and crosslingual models help bring different languages together in a language universal space.
The Second Conversational Intelligence Challenge (ConvAI2)
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots.
Multimodal Polynomial Fusion for Detecting Driver Distraction
Distracted driving is deadly, claiming 3, 477 lives in the U. S. in 2015 alone.
A Dataset for Document Grounded Conversations
We define "Document Grounded Conversations" as conversations that are about the contents of a specified document.
Data Augmentation for Neural Online Chat Response Selection
Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models.
Domain Robust Feature Extraction for Rapid Low Resource ASR Development
We demonstrate the effectiveness of using a pre-trained English recognizer, which is robust to such mismatched conditions, as a domain normalizing feature extractor on a low resource language.
Generating Mandarin and Cantonese F0 Contours with Decision Trees and BLSTMs
This paper models the fundamental frequency contours on both Mandarin and Cantonese speech with decision trees and DNNs (deep neural networks).
Language Informed Modeling of Code-Switched Text
Code-switching (CS), the practice of alternating between two or more languages in conversations, is pervasive in most multi-lingual communities.
Automatic Detection of Code-switching Style from Acoustics
We hypothesize that it may be useful for an ASR system to be able to first detect the switching style of a particular utterance from acoustics, and then use specialized language models or other adaptation techniques for decoding the speech.
Automatic Speech Recognition (ASR)
Language Identification
+1
Tackling Code-Switched NER: Participation of CMU
In this paper we describe models that intuitively developed from the data for the shared task Named Entity Recognition on Code-switched Data.
An Empirical Study of Self-Disclosure in Spoken Dialogue Systems
Self-disclosure is a key social strategy employed in conversation to build relations and increase conversational depth.
DialCrowd: A toolkit for easy dialog system assessment
When creating a dialog system, developers need to test each version to ensure that it is performing correctly.
Code-Mixed Question Answering Challenge: Crowd-sourcing Data and Techniques
As a first step towards fostering research which supports CM in NLP applications, we systematically crowd-sourced and curated an evaluation dataset for factoid question answering in three CM languages - Hinglish (Hindi+English), Tenglish (Telugu+English) and Tamlish (Tamil+English) which belong to two language families (Indo-Aryan and Dravidian).
Style Transfer Through Back-Translation
We first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties.
Ranked #10 on
Unsupervised Text Style Transfer
on Yelp
Sequence-based Multi-lingual Low Resource Speech Recognition
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains.
Linguistic Markers of Influence in Informal Interactions
There has been a long standing interest in understanding `Social Influence' both in Social Sciences and in Computational Linguistics.
Learning Conversational Systems that Interleave Task and Non-Task Content
These systems work well when users have clear and explicit intentions that are well-aligned to the systems' capabilities.
Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning
We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted.
Speech Synthesis of Code-Mixed Text
Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in.
Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis
In the last two years, there have been numerous papers that have looked into using Deep Neural Networks to replace the acoustic model in traditional statistical parametric speech synthesis.
Character-based Neural Machine Translation
We introduce a neural machine translation model that views the input and output sentences as sequences of characters rather than words.
Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs.
Ranked #4 on
Part-Of-Speech Tagging
on Penn Treebank
A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis
Mel Cepstral coefficients were never intended to work in a parametric speech synthesis framework, but as yet, there has been little success in creating a better parameterization that is more suited to synthesis.
