The recent growth in the popularity and success of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of the predicted labels. Such generated natural language (NL) explanations are expected to be faithful, i.e., they should correlate well with the model's internal decision making. In this work, we focus on the task of natural language inference (NLI) and address the following question: can we build NLI systems which produce labels with high accuracy, while also generating faithful explanations of its decisions? We propose Naturallanguage Inference over Label-specific Explanations (NILE), a novel NLI method which utilizes auto-generated label-specific NL explanations to produce labels along with its faithful explanation. We demonstrate NILE's effectiveness over previously reported methods through automated and human evaluation of the produced labels and explanations. Our evaluation of NILE also supports the claim that accurate systems capable of providing testable explanations of their decisions can be designed. We discuss the faithfulness of NILE's explanations in terms of sensitivity of the decisions to the corresponding explanations. We argue that explicit evaluation of faithfulness, in addition to label and explanation accuracy, is an important step in evaluating model's explanations. Further, we demonstrate that task-specific probes are necessary to establish such sensitivity.
Word Sense Disambiguation (WSD) is a longstanding but open problem in Natural Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive annotation process. Current supervised WSD methods treat senses as discrete labels and also resort to predicting the Most-Frequent-Sense (MFS) for words unseen during training. This leads to poor performance on rare and unseen senses. To overcome this challenge, we propose Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space. This allows EWISE to generalize over both seen and unseen senses, thus achieving generalized zeroshot learning. To obtain target sense embeddings, EWISE utilizes sense definitions. EWISE learns a novel sentence encoder for sense definitions by using WordNet relations and also ConvE, a recently proposed knowledge graph embedding method. We also compare EWISE against other sentence encoders pretrained on large corpora to generate definition embeddings. EWISE achieves new stateof-the-art WSD performance.
In this investigation, the application of citric acid was explored for the removal of extracellular polymeric substance (EPS) from waste activated sludge (WAS), followed by ultrasonic pretreatment, which enhanced the subsequent anaerobic biodegradability. EPS was removed with 0.05g/g SS of citric acid. The chemical oxygen demand (COD) solubilization and suspended solids (SS) reduction that occurred for specific energy input of 171.9kJ/kg TS, in deflocculated (EPS removed and ultrasonically pretreated) sludges were found to be 22.70% and 20.28% and was comparatively higher, than the flocculated (with EPS and ultrasonically pretreated). The biogas yield potential of flocculated and deflocculated sludges (specific energy input - 171.9kJ/kgTS) was found to be 0.212L/(gVS) and 0.435L/(gVS), respectively. Accordingly, the deflocculation and ultrasonic pretreatment improved the anaerobic biodegradability efficiently. Thus, this chemo mediated sonic pretreatment is an effective method for enhancing biodegradability and improving clean energy generation from WAS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.