Previous work has shown that automated essay scoring systems, in particular machine learning-based systems, are not capable of assessing the quality of essays, but are relying on essay length, a factor irrelevant to writing proficiency. In this work,
we first show that state-of-the-art systems, recent neural essay scoring systems, might be also influenced by the correlation between essay length and scores in a standard dataset. In our evaluation, a very simple neural model shows the state-of-the-art performance on the standard dataset. To consider essay content without taking essay length into account, we introduce a simple neural model assessing the similarity of content between an input essay and essays assigned different scores. This neural model achieves performance comparable to the state of the art on a standard dataset as well as on a second dataset. Our findings suggest that neural essay scoring systems should consider the characteristics of datasets to focus on text quality.
A nominalization uses a deverbal noun to describe an event associated with its underlying verb. Commonly found in academic and formal texts, nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal no
un and its arguments. Our goal is to interpret nominalizations by generating clausal paraphrases. We address compound nominalizations with both nominal and adjectival modifiers, as well as prepositional phrases. In evaluations on a number of unsupervised methods, we obtained the strongest performance by using a pre-trained contextualized language model to re-rank paraphrase candidates identified by a textual entailment model.
The automatic evaluation of open-domain dialogues remains a largely unsolved challenge. Despite the abundance of work done in the field, human judges have to evaluate dialogues' quality. As a consequence, performing such evaluations at scale is usual
ly expensive. This work investigates using a deep-learning model trained on the General Language Understanding Evaluation (GLUE) benchmark to serve as a quality indication of open-domain dialogues. The aim is to use the various GLUE tasks as different perspectives on judging the quality of conversation, thus reducing the need for additional training data or responses that serve as quality references. Due to this nature, the method can infer various quality metrics and can derive a component-based overall score. We achieve statistically significant correlation coefficients of up to 0.7.
In this paper, we study the possibility of unsupervised Multiple Choices Question Answering (MCQA). From very basic knowledge, the MCQA model knows that some choices have higher probabilities of being correct than others. The information, though very
noisy, guides the training of an MCQA model. The proposed method is shown to outperform the baseline approaches on RACE and is even comparable with some supervised learning approaches on MC500.
For interpreting the behavior of a probabilistic model, it is useful to measure a model's calibration---the extent to which it produces reliable confidence scores. We address the open problem of calibration for tagging models with sparse tagsets, and
recommend strategies to measure and reduce calibration error (CE) in such models. We show that several post-hoc recalibration techniques all reduce calibration error across the marginal distribution for two existing sequence taggers. Moreover, we propose tag frequency grouping (TFG) as a way to measure calibration error in different frequency bands. Further, recalibrating each group separately promotes a more equitable reduction of calibration error across the tag frequency spectrum.
As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true capabilities. For a
more informative evaluation than accuracy on text classification tasks can offer, we propose evaluating systems through a novel measure of prediction coherence. We apply our framework to two existing language understanding benchmarks with different properties to demonstrate its versatility. Our experimental results show that this evaluation framework, although simple in ideas and implementation, is a quick, effective, and versatile measure to provide insight into the coherence of machines' predictions.
Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks t
hat are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attenti
on Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in MultiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplified sparse training scenario in which DST models are trained only on session-level annotations but evaluated at the turn level. We further report detailed analyses to demonstrate the effectiveness of graph models in DST by showing that the proposed graph modules capture inter-slot dependencies and improve the predictions of values that are common to multiple domains.
Much of the progress in contemporary NLP has come from learning representations, such as masked language model (MLM) contextual embeddings, that turn challenging problems into simple classification tasks. But how do we quantify and explain this effec
t? We adapt general tools from computational learning theory to fit the specific characteristics of text datasets and present a method to evaluate the compatibility between representations and tasks. Even though many tasks can be easily solved with simple bag-of-words (BOW) representations, BOW does poorly on hard natural language inference tasks. For one such task we find that BOW cannot distinguish between real and randomized labelings, while pre-trained MLM representations show 72x greater distinction between real and random labelings than BOW. This method provides a calibrated, quantitative measure of the difficulty of a classification-based NLP task, enabling comparisons between representations without requiring empirical evaluations that may be sensitive to initializations and hyperparameters. The method provides a fresh perspective on the patterns in a dataset and the alignment of those patterns with specific labels.
While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional preprocessi
ng tools for VSDs mainly focused on word segmentation and coarse layout analysis, whereas fine-grained logical structure analysis (such as identifying paragraph boundaries and their hierarchies) of VSDs is underexplored. To that end, we proposed to formulate the task as prediction of transition labels'' between text fragments that maps the fragments to a tree, and developed a feature-based machine learning system that fuses visual, textual and semantic cues. Our system is easily customizable to different types of VSDs and it significantly outperformed baselines in identifying different structures in VSDs. For example, our system obtained a paragraph boundary detection F1 score of 0.953 which is significantly better than a popular PDF-to-text tool with an F1 score of 0.739.
