Related papers: Adaptative Bilingual Aligning Using Multilingual S…

Text simplification plays a crucial role in improving the accessibility and comprehensibility of written information for diverse audiences, including language learners and readers with limited literacy. Despite its importance, large-scale,…

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word…

Modern neural networks have greatly improved performance across speech recognition benchmarks. However, gains are often driven by frequent words with limited semantic weight, which can obscure meaningful differences in word error rate, the…

Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-of-speech tagging and sentence alignment. End-of-sentence punctuation marks are ambiguous; to disambiguate them most…

Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from…

This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern…

Social network alignment aims at aligning person identities across social networks. Embedding based models have been shown effective for the alignment where the structural proximity preserving objective is typically adopted for the model…

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. In this paper, we instead propose a generative model for learning…

Contextual adaptation in token embeddings plays a central role in determining how well language models maintain coherence and retain semantic relationships over extended text sequences. Static embeddings often impose constraints on lexical…

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this…

Cross-lingual information retrieval is a challenging task in the absence of aligned parallel corpora. In this paper, we address this problem by considering topically aligned corpora designed for evaluating an IR setup. To emphasize, we…

With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on…

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching.…

We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered…

This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a…

Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

Autoregressive Large Language Models (LLMs) demonstrate exceptional performance in language understanding and generation. However, their application in text embedding tasks has been relatively slow, along with the analysis of their semantic…

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…