Search Results for author: Sachin Kumar

Found 27 papers, 11 papers with code

What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization

1 code implementation16 Nov 2023 YuHan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov

In this work, we take a first step towards designing summarization systems that are faithful to the author's opinions and perspectives.

News Summarization

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

no code implementations13 Nov 2023 Sachin Kumar, Chan Young Park, Yulia Tsvetkov

GEN-Z is generative, as it measures the LM likelihood of input text, conditioned on natural language descriptions of labels.

Language Modelling text-classification +3

Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker

no code implementations1 Jun 2023 Melanie Sclar, Sachin Kumar, Peter West, Alane Suhr, Yejin Choi, Yulia Tsvetkov

We present SymbolicToM, a plug-and-play approach to reason about the belief states of multiple characters in reading comprehension tasks via explicit symbolic representation.

Reading Comprehension

David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs

no code implementations24 May 2023 Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov, Marjan Ghazvininejad

Diffusion-based language models are emerging as a promising alternative to autoregressive LMs: they approach the competence of autoregressive LMs while offering nuanced controllability at inference time.

Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models

no code implementations23 May 2023 Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Jungo Kasai, David R. Mortensen, Noah A. Smith, Yulia Tsvetkov

Language models have graduated from being research prototypes to commercialized products offered as web APIs, and recent works have highlighted the multilingual capabilities of these products.

Fairness Language Modelling

Assessing Language Model Deployment with Risk Cards

2 code implementations31 Mar 2023 Leon Derczynski, Hannah Rose Kirk, Vidhisha Balachandran, Sachin Kumar, Yulia Tsvetkov, M. R. Leiser, Saif Mohammad

However, there is no risk-centric framework for documenting the complexity of a landscape in which some risks are shared across models and contexts, while others are specific, and where certain conditions may be required for risks to manifest as harms.

Language Modelling Text Generation

On the Blind Spots of Model-Based Evaluation Metrics for Text Generation

1 code implementation20 Dec 2022 Tianxing He, Jingyu Zhang, Tianle Wang, Sachin Kumar, Kyunghyun Cho, James Glass, Yulia Tsvetkov

In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data.

Text Generation

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

1 code implementation31 Oct 2022 Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov

Despite the growing success of diffusion models in continuous-valued domains (e. g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models.

Language Modelling Text Generation

Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation

no code implementations25 Oct 2022 Melanie Sclar, Peter West, Sachin Kumar, Yulia Tsvetkov, Yejin Choi

Moreover, we uniquely propose iterative distillation of knowledge, where student models from the previous iteration of distillation serve as teacher models in the next iteration.

Knowledge Distillation Sentence +1

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey

no code implementations14 Oct 2022 Sachin Kumar, Vidhisha Balachandran, Lucille Njoo, Antonios Anastasopoulos, Yulia Tsvetkov

Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings.

Language Modelling Text Generation

Gradient-Based Constrained Sampling from Language Models

no code implementations25 May 2022 Sachin Kumar, Biswajit Paria, Yulia Tsvetkov

Large pretrained language models generate fluent text but are notoriously hard to controllably sample from.

Language Modelling Text Generation

Controlled Text Generation as Continuous Optimization with Multiple Constraints

1 code implementation NeurIPS 2021 Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate.

Language Modelling Machine Translation +4

Machine Translation into Low-resource Language Varieties

no code implementations ACL 2021 Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, Yulia Tsvetkov

State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language.

Machine Translation Translation

An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation

no code implementations31 Mar 2021 Lidia Kidane, Sachin Kumar, Yulia Tsvetkov

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, often requiring large amounts of auxiliary data to achieve competitive results.

Data Augmentation Machine Translation +2

CAMTA: Causal Attention Model for Multi-touch Attribution

no code implementations21 Dec 2020 Sachin Kumar, Garima Gupta, Ranjitha Prasad, Arnab Chatterjee, Lovekesh Vig, Gautam Shroff

Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc.

Selection bias

End-to-End Differentiable GANs for Text Generation

no code implementations NeurIPS Workshop ICBINB 2020 Sachin Kumar, Yulia Tsvetkov

We posit that this gap is due to autoregressive nature and architectural requirements for text generation as well as a fundamental difference between the definition of Wasserstein distance in image and text domains.

Text Generation

A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards

1 code implementation WS 2020 Zi-Yi Dou, Sachin Kumar, Yulia Tsvetkov

The model uses reinforcement learning to directly optimize a bilingual semantic similarity metric between the summaries generated in a target language and gold summaries in a source language.

Machine Translation reinforcement-learning +5

Neural Abstractive Summarization with Structural Attention

no code implementations21 Apr 2020 Tanya Chowdhury, Sachin Kumar, Tanmoy Chakraborty

This problem is exacerbated in multi-document summarization tasks such as summarizing the popular opinion in threads present in community question answering (CQA) websites such as Yahoo!

Abstractive Text Summarization Community Question Answering +3

A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation

no code implementations WS 2019 Gayatri Bhat, Sachin Kumar, Yulia Tsvetkov

Neural models that eliminate the softmax bottleneck by generating word embeddings (rather than multinomial distributions over a vocabulary) attain faster training with fewer learnable parameters.

Machine Translation Translation +1

Topics to Avoid: Demoting Latent Confounds in Text Classification

1 code implementation IJCNLP 2019 Sachin Kumar, Shuly Wintner, Noah A. Smith, Yulia Tsvetkov

Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well.

General Classification Native Language Identification +2

Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs

1 code implementation ICLR 2019 Sachin Kumar, Yulia Tsvetkov

The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation.

Machine Translation Text Generation +2

Precision Sugarcane Monitoring Using SVM Classifier

no code implementations26 Mar 2018 Sachin Kumar, Sumita Mishra, Pooja Khanna, Pragya

India is agriculture based economy and sugarcane is one of the major crops produced in northern India.

Clustering

Automated Detection of Acute Leukemia using K-mean Clustering Algorithm

no code implementations6 Mar 2018 Sachin Kumar, Sumita Mishra, Pallavi Asthana, Pragya

Leukemia is a hematologic cancer which develops in blood tissue and triggers rapid production of immature and abnormal shaped white blood cells.

Clustering

System and Methods for Converting Speech to SQL

no code implementations14 Aug 2013 Sachin Kumar, Ashish Kumar, Pinaki Mitra, Girish Sundaram

For conversion of speech into English text HTK and Julius tools have been used and for conversion of English text query into SQL query we have implemented a System which uses rule based translation to translate English Language Query into SQL Query.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.