Search Results for author:
Found 39 papers, 22 papers with code
CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step.
Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval
Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well.
compare-mt: A Tool for Holistic Comparison of Language Generation Systems
In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation.
Reformulating Unsupervised Style Transfer as Paraphrase Generation
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs.
No Training Required: Exploring Random Encoders for Sentence Classification
We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i. e., using nothing but random parameterizations.
Adversarial Example Generation with Syntactically Controlled Paraphrase Networks
We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples.
RankGen: Improving Text Generation with Large Ranking Models
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts.
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
To increase the robustness of AI-generated text detection to paraphrase attacks, we introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
Simple and Effective Paraphrastic Similarity from Parallel Translations
We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating paraphrase corpora.
Paraphrastic Representations at Scale
We train these models on large amounts of data, achieving significantly improved performance from the original papers proposing the methods on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks.
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve final translation accuracy.
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
We evaluate commonly used models on the benchmark.
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
Therefore, to study model capabilities across both cross-lingual and monolingual retrieval tasks, we develop SWIM-IR, a synthetic retrieval training dataset containing 33 (high to very-low resource) languages for training multilingual dense retrieval models without requiring any human supervision.
A Gold Standard Dataset for the Reviewer Assignment Problem
We address this challenge by collecting a novel dataset of similarity scores that we release to the research community.
Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Using Par3, we discover that expert literary translators prefer reference human translations over machine-translated paragraphs at a rate of 84%, while state-of-the-art automatic MT metrics do not correlate with those preferences.
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts.
PaLM 2 Technical Report
Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.
Ranked #1 on
Question Answering
on StrategyQA
A Bilingual Generative Transformer for Semantic Sentence Embedding
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences.
On Learning Text Style Transfer with Direct Rewards
In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task.
Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
We present a novel technique for zero-shot paraphrase generation.
ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations
We describe PARANMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs.
Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b).
Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b).
Charagram: Embedding Words and Sentences via Character n-grams
We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences.
Towards Universal Paraphrastic Sentence Embeddings
We again find that the word averaging models perform well for sentence similarity and entailment, outperforming LSTMs.
Clustering With Side Information: From a Probabilistic Model to a Deterministic Algorithm
Empirical studies have been carried out to compare our work with many constrained clustering algorithms from the literature on both a variety of data sets and under a variety of conditions such as using noisy side information and erroneous k values.
From Paraphrase Database to Compositional Paraphrase Model and Back
The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates.
Tiered Clustering to Improve Lexical Entailment
The second is a supervised approach where a classifier is learned to predict entailment given a concatenated latent vector representation of the word.
Quality Signals in Generated Stories
We study the problem of measuring the quality of automatically-generated stories.
Beyond BLEU:Training Neural Machine Translation with Semantic Similarity
While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy.
On The Ingredients of an Effective Zero-shot Semantic Parser
Semantic parsers map natural language utterances into meaning representations (e. g., programs).
Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
Retrieval augmented language models have recently become the standard for knowledge intensive tasks.
Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
In this work, we show that these entities are not aberrations, but they instead require utilizing external world knowledge to infer reasoning paths from entities in the source.
QA Is the New KR: Question-Answer Pairs as Knowledge Bases
In this position paper, we propose a new approach to generating a type of knowledge base (KB) from text, based on question generation and entity linking.
Evaluating and Modeling Attribution for Cross-Lingual Question Answering
Based on these models, we improve the attribution level of a cross-lingual question-answering system.
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
