We present STAGE, a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages Large-Language Models (LLMs) to generate embeddings for textual attributes. STAGE achieves competitive results on various node classification benchmarks while also maintaining a simplicity in implementation relative to current state-of-the-art (SoTA) techniques. We show that utilizing pre-trained LLMs as embedding generators provides robust features for ensemble GNN training, enabling pipelines that are simpler than current SoTA approaches which require multiple expensive training and prompting stages. We also implement diffusion-pattern GNNs in an effort to make this pipeline scalable to graphs beyond academic benchmarks.

We present an open-source Python library for building and using datasets where inputs are clusters of textual data, and outputs are sequences of real values representing one or more timeseries signals. The news-signals library supports diverse data science and NLP problem settings related to the prediction of time series behaviour using textual data feeds. For example, in the news domain, inputs are document clusters corresponding to daily news articles about a particular entity, and targets are explicitly associated real-valued timeseries: the volume of news about a particular person or company, or the number of pageviews of specific Wikimedia pages. Despite many industry and research usecases for this class of problem settings, to the best of our knowledge, News Signals is the only open-source library designed specifically to facilitate data science and research settings with natural language inputs and timeseries targets. In addition to the core codebase for building and interacting with datasets, we also conduct a suite of experiments using several popular Machine Learning libraries, which are used to establish baselines for timeseries anomaly prediction using textual inputs.

Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models without the need for ground-truth training data, while allowing flexibility in the objective function(s) that are used for learning and inference. Recent unsupervised sentence compression approaches use custom objectives to guide discrete search; however, guided search is expensive at inference time. In this work, we explore the use of reinforcement learning to train effective sentence compression models that are also fast when generating predictions. In particular, we cast the task as binary sequence labelling and fine-tune a pre-trained transformer using a simple policy gradient approach. Our approach outperforms other unsupervised models while also being more efficient at inference time.

Multi-document summarization (MDS) aims to compress the content in large document collections into short summaries and has important applications in story clustering for newsfeeds, presentation of search results, and timeline generation. However, there is a lack of datasets that realistically address such use cases at a scale large enough for training supervised models for this task. This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters. We build this dataset by leveraging the Wikipedia Current Events Portal (WCEP), which provides concise and neutral human-written summaries of news events, with links to external source articles. We also automatically extend these source articles by looking for related articles in the Common Crawl archive. We provide a quantitative analysis of the dataset and empirical results for several state-of-the-art MDS techniques.

We study several methods for full or partial sharing of the decoder parameters of multi-lingual NMT models. Using only the WMT 2019 shared task parallel datasets for training, we evaluate both fully supervised and zero-shot translation performance in 110 unique translation directions. We use additional test sets and re-purpose evaluation methods recently used for unsupervised MT in order to evaluate zero-shot translation performance for language pairs where no gold-standard parallel data is available. To our knowledge, this is the largest evaluation of multi-lingual translation yet conducted in terms of the total size of the training data we use, and in terms of the number of zero-shot translation pairs we evaluate. We conduct an in-depth evaluation of the translation performance of different models, highlighting the trade-offs between methods of sharing decoder parameters. We find that models which have task-specific decoder parameters outperform models where decoder parameters are fully shared across all tasks.

This work presents state of the art results in reconstruction of surface realizations from obfuscated text. We identify the lack of sufficient training data as the major obstacle to training high-performing models, and solve this issue by generating large amounts of synthetic training data. We also propose preprocessing techniques which make the structure contained in the input features more accessible to sequence models. Our models were ranked first on all evaluation metrics in the English portion of the 2018 Surface Realization shared task.

Translation quality estimation is a task of growing importance in NLP, due to its potential to reduce post-editing human effort in disruptive ways. However, this potential is currently limited by the relatively low accuracy of existing systems. In this paper, we achieve remarkable improvements by exploiting synergies between the related tasks of word-level quality estimation and automatic post-editing. First, we stack a new, carefully engineered, neural model into a rich feature-based word-level quality estimation system. Then, we use the output of an automatic post-editing system as an extra feature, obtaining striking results on WMT16: a word-level FMULT1 score of 57.47% (an absolute gain of +7.95% over the current state of the art), and a Pearson correlation score of 65.56% for sentence-level HTER prediction (an absolute gain of +13.36%).

We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model which generates sequences token by token. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate auxillary knowledge into a model’s output without requiring any modification of the parameters or training data. We demonstrate the feasibility and flexibility of Lexically Constrained Decoding by conducting experiments on Neural Interactive-Predictive Translation, as well as Domain Adaptation for Neural Machine Translation. Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, GBS can be used to achieve significant gains in performance in domain adaptation scenarios.

We present Marmot~― a new toolkit for quality estimation (QE) of machine translation output. Marmot contains utilities targeted at quality estimation at the word and phrase level. However, due to its flexibility and modularity, it can also be extended to work at the sentence level. In addition, it can be used as a framework for extracting features and learning models for many common natural language processing tasks. The tool has a set of state-of-the-art features for QE, and new features can easily be added. The tool is open-source and can be downloaded from https://github.com/qe-team/marmot/

We describe the results of several experiments with interactive interfaces for native and L2 English students, designed to collect implicit feedback from students as they complete a reading activity. In this study, implicit means that all data is obtained without asking the user for feedback. To test the value of implicit feedback for assessing student proficiency, we collect features of user behavior and interaction, which are then used to train classification models. Based upon the feedback collected during these experiments, a student’s performance on a quiz and proficiency relative to other students can be accurately predicted, which is a step on the path to our goal of providing automatic feedback and unintrusive evaluation in interactive learning environments.