相关论文: Found in Translation: Reconstructing Phylogenetic …
Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform…
As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help…
Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…
Generating natural language requires conveying content in an appropriate style. We explore two related tasks on generating text of varying formality: monolingual formality transfer and formality-sensitive machine translation. We propose to…
Language is a cornerstone of cultural identity, yet globalization and the dominance of major languages have placed nearly 3,000 languages at risk of extinction. Existing AI-driven translation models prioritize efficiency but often fail to…
Understanding the evolution of a set of genes or species is a fundamental problem in evolutionary biology. The problem we study here takes as input a set of trees describing {possibly discordant} evolutionary scenarios for a given set of…
In mathematical phylogenetics, evolutionary relationships are often represented by trees and networks. The latter are typically used whenever the relationships cannot be adequately described by a tree, which happens when so-called…
A large class of phylogenetic networks can be obtained from trees by the addition of horizontal edges between the tree edges. These networks are called tree based networks. Reticulation-visible networks and child-sibling networks are all…
Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a…
Our book "The Reality of Multi-Lingual Machine Translation" discusses the benefits and perils of using more than two languages in machine translation systems. While focused on the particular task of sequence-to-sequence processing and…
Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context. This paper introduces a new method for automatic style transfer. We first learn a latent…
Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM), which uses special tokens to encode branching structure,…
Multilingual pre-trained language models transfer remarkably well on cross-lingual downstream tasks. However, the extent to which they learn language-neutral representations (i.e., shared representations that encode similar phenomena across…
LLMs are proving to be adept at machine translation although due to their generative nature they may at times overgenerate in various ways. These overgenerations are different from the neurobabble seen in NMT and range from LLM…
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…
Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language model has an input layer that maps tokens to vectors. This…
The reconstruction of phylogenies from DNA or protein sequences is a major task of computational evolutionary biology. Common phenomena, notably variations in mutation rates across genomes and incongruences between gene lineage histories,…
Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…
Rooted phylogenetic networks provide a way to describe species' relationships when evolution departs from the simple model of a tree. However, networks inferred from genomic data can be highly tangled, making it difficult to discern the…
It is well known that attributed tree transducers can be equipped with "regular look-around" in order to obtain a more robust class of translations. We present two characterizations of this class in terms of macro tree transducers (MTTs):…