Related papers: Misspelling Semantics In Thai
The primary objective of our work is to build a large-scale English-Thai dataset for machine translation. We construct an English-Thai machine translation dataset with over 1 million segment pairs, curated from various sources, namely news,…
Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most…
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the…
RTE is a significant problem and is a reasonably active research community. The proposed research works on the approach to this problem are pretty diverse with many different directions. For Vietnamese, the RTE problem is moderately new,…
Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training distributions. Recent work demonstrates compartmentalization of misalignment behind contextual…
With the enourmous popularity of large language models, many researchers have raised ethical concerns regarding social biases incorporated in such models. Several methods to measure social bias have been introduced, but apparently these…
Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…
Text normalization is an essential preprocessing step in many natural language processing (NLP) tasks, and stemming is one such normalization technique that reduces words to their base or root form. However, evaluating stemming methods is…
This paper explores the pitfalls in evaluating multilingual automatic speech recognition (ASR) models, with a particular focus on Indic language scripts. We investigate the text normalization routine employed by leading ASR models,…
In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain a non-negligible amount of out-of-vocabulary words. We…
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuning leverages the…
Fine-grained sentiment analysis is receiving increasing attention in recent years. Extracting opinion target expressions (OTE) in reviews is often an important step in fine-grained, aspect-based sentiment analysis. Retrieving this…
Increasing interpreting needs a more objective and automatic measurement. We hold a basic idea that 'translating means translating meaning' in that we can assessment interpretation quality by comparing the meaning of the interpreting output…
As Machine Translation (MT) becomes increasingly commonplace, understanding how the general public perceives and relies on imperfect MT is crucial for contextualizing MT research in real-world applications. We present a human study…
Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from…
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model…
Understanding sentiment in financial documents is crucial for gaining insights into market behavior. These reports often contain obfuscated language designed to present a positive or neutral outlook, even when underlying conditions may be…
Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…
Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additional resources. We…
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, specifically superficial…