Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained. However, despite the success of LLMs, there has been little understanding of how ICL learns the knowledge from the given prompts. In this paper, to make progress toward understanding the learning behaviour of ICL, we train the same LLMs with the same demonstration examples via ICL and supervised learning (SL), respectively, and investigate their performance under label perturbations (i.e., noisy labels and label imbalance) on a range of classification tasks. First, via extensive experiments, we find that gold labels have significant impacts on the downstream in-context performance, especially for large language models; however, imbalanced labels matter little to ICL across all model sizes. Second, when comparing with SL, we show empirically that ICL is less sensitive to label perturbations than SL, and ICL gradually attains comparable performance to SL as the model size increases.
Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms. Currently, the vast number of biomedical articles in the PubMed database are manually annotated by human curators, which is time consuming and costly; therefore, a computational system that can assist the indexing is highly valuable. When developing supervised MeSH indexing systems, the availability of a large-scale annotated text corpus is desirable. A publicly available, large corpus that permits robust evaluation and comparison of various systems is important to the research community. We release a large scale annotated MeSH indexing corpus, MeSHup, which contains 1,342,667 full text articles in English, together with the associated MeSH labels and metadata, authors, and publication venues that are collected from the MEDLINE database. We train an end-to-end model that combines features from documents and their associated labels on our corpus and report the new baseline.
Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate these models. In the case of Spanish, there are few ways to systematically assess the models' quality. In this paper, we narrow the gap by building two evaluation benchmarks. Inspired by previous work (Conneau and Kiela, 2018; Chen et al., 2019), we introduce Spanish SentEval and Spanish DiscoEval, aiming to assess the capabilities of stand-alone and discourse-aware sentence representations, respectively. Our benchmarks include considerable pre-existing and newly constructed datasets that address different tasks from various domains. In addition, we evaluate and analyze the most recent pre-trained Spanish language models to exhibit their capabilities and limitations. As an example, we discover that for the case of discourse evaluation tasks, mBERT, a language model trained on multiple languages, usually provides a richer latent representation than models trained only with documents in Spanish. We hope our contribution will motivate a fairer, more comparable, and less cumbersome way to evaluate future Spanish language models.
Currently, Medical Subject Headings (MeSH) are manually assigned to every biomedical article published and subsequently recorded in the PubMed database to facilitate retrieving relevant information. With the rapid growth of the PubMed database, large-scale biomedical document indexing becomes increasingly important. MeSH indexing is a challenging task for machine learning, as it needs to assign multiple labels to each article from an extremely large hierachically organized collection. To address this challenge, we propose KenMeSH, an end-to-end model that combines new text features and a dynamic \textbf{K}nowledge-\textbf{en}hanced mask attention that integrates document features with MeSH label hierarchy and journal correlation features to index MeSH terms. Experimental results show the proposed method achieves state-of-the-art performance on a number of measures.
In Natural Language Processing (NLP), we often need to extract information from tree topology. Sentence structure can be represented via a dependency tree or a constituency tree structure. For this reason, a variant of LSTMs, named Tree-LSTM, was proposed to work on tree topology. In this paper, we design a generalized attention framework for both dependency and constituency trees by encoding variants of decomposable attention inside a Tree-LSTM cell. We evaluated our models on a semantic relatedness task and achieved notable results compared to Tree-LSTM based methods with no attention as well as other neural and non-neural methods and good results compared to Tree-LSTM based methods with attention.
Word sense disambiguation (WSD) is a well researched problem in computational linguistics. Different research works have approached this problem in different ways. Some state of the art results that have been achieved for this problem are by supervised models in terms of accuracy, but they often fall behind flexible knowledge-based solutions which use engineered features as well as human annotators to disambiguate every target word. This work focuses on bridging this gap using neural sequence models incorporating the well-known attention mechanism. The main gist of our work is to combine multiple attentions on different linguistic features through weights and to provide a unified framework for doing this. This weighted attention allows the model to easily disambiguate the sense of an ambiguous word by attending over a suitable portion of a sentence. Our extensive experiments show that multiple attention enables a more versatile encoder-decoder model leading to state of the art results.
Identifying interactions between proteins is important to understand underlying biological processes. Extracting a protein-protein interaction (PPI) from the raw text is often very difficult. Previous supervised learning methods have used handcrafted features on human-annotated data sets. In this paper, we propose a novel tree recurrent neural network with structured attention architecture for doing PPI. Our architecture achieves state of the art results (precision, recall, and F1-score) on the AIMed and BioInfer benchmark data sets. Moreover, our models achieve a significant improvement over previous best models without any explicit feature extraction. Our experimental results show that traditional recurrent networks have inferior performance compared to tree recurrent networks for the supervised PPI problem.
Sequence labelling is the task of assigning categorical labels to a data sequence. In Natural Language Processing, sequence labelling can be applied to various fundamental problems, such as Part of Speech (POS) tagging, Named Entity Recognition (NER), and Chunking. In this study, we propose a method to add various linguistic features to the neural sequence framework to improve sequence labelling. Besides word level knowledge, sense embeddings are added to provide semantic information. Additionally, selective readings of character embeddings are added to capture contextual as well as morphological features for each word in a sentence. Compared to previous methods, these added linguistic features allow us to design a more concise model and perform more efficient training. Our proposed architecture achieves state of the art results on the benchmark datasets of POS, NER, and chunking. Moreover, the convergence rate of our model is significantly better than the previous state of the art models.
In this paper, we establish Fog Index (FI) as a text filter to locate the sentences in texts that contain connected biomedical concepts of interest. To do so, we have used 24 random papers each containing four pairs of connected concepts. For each pair, we categorize sentences based on whether they contain both, any or none of the concepts. We then use FI to measure difficulty of the sentences of each category and find that sentences containing both of the concepts have low readability. We rank sentences of a text according to their FI and select 30 percent of the most difficult sentences. We use an association matrix to track the most frequent pairs of concepts in them. This matrix reports that the first filter produces some pairs that hold almost no connections. To remove these unwanted pairs, we use the Equally Weighted Harmonic Mean of their Positive Predictive Value (PPV) and Sensitivity as a second filter. Experimental results demonstrate the effectiveness of our method.
We propose a new approach to belief revision that provides a way to change knowledge bases with a minimum of effort. We call this way of revising belief states optimal belief revision. Our revision method gives special attention to the fact that most belief revision processes are directed to a specific informational objective. This approach to belief change is founded on notions such as optimal context and accessibility. For the sentential model of belief states we provide both a formal description of contexts as sub-theories determined by three parameters and a method to construct contexts. Next, we introduce an accessibility ordering for belief sets, which we then use for selecting the best (optimal) contexts with respect to the processing effort involved in the revision. Then, for finitely axiomatizable knowledge bases, we characterize a finite accessibility ranking from which the accessibility ordering for the entire base is generated and show how to determine the ranking of an arbitrary sentence in the language. Finally, we define the adjustment of the accessibility ranking of a revised base of a belief set.