Annotation inconsistencies between data sets can cause problems for low-resource NLP, where noisy or inconsistent data cannot be easily replaced. We propose a method for automatically detecting annotation mismatches between dependency parsing corpora, along with three related methods for automatically converting the mismatches. All three methods rely on comparing unseen examples in a new corpus with similar examples in an existing corpus. These three methods include a simple lexical replacement using the most frequent tag of the example in the existing corpus, a GloVe embedding-based replacement that considers related examples, and a BERT-based replacement that uses contextualized embeddings to provide examples fine-tuned to our data. We evaluate these conversions by retraining two dependency parsers—Stanza and Parsing as Tagging (PaT)—on the converted and unconverted data. We find that applying our conversions yields significantly better performance in many cases. Some differences observed between the two parsers are observed. Stanza has a more complex architecture with a quadratic algorithm, taking longer to train, but it can generalize from less data. The PaT parser has a simpler architecture with a linear algorithm, speeding up training but requiring more training data to reach comparable or better performance.

Rebecca Sharp, Mihai Surdeanu, Peter Jansen, Marco A. Valenzuela-Escárcega, Peter Clark, Michael Hammond. Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). 2017.

A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using generalpurpose lexical models such as word embeddings.We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings.With causality as a use case, we implement this insight in three steps.First, we generate causal embeddings cost-effectively by bootstrapping cause-effect pairs extracted from free text using a small set of seed patterns.Second, we train dedicated embeddings over this data, by using task-specific contexts, i.e., the context of a cause is its effect.Finally, we extend a state-of-the-art reranking approach for QA to incorporate these causal embeddings.We evaluate the causal embedding models both directly with a casual implication task, and indirectly, in a downstream causal QA task using data from Yahoo! Answers.We show that explicitly modeling causality improves performance in both tasks.In the QA task our best model achieves 37.3% P@1, significantly outperforming a strong baseline by 7.7% (relative).

The emerging smart health and smart home applications require pervasive and non-intrusive human activity recognition and monitoring. Traditional technologies (e.g., using cameras or accelerometers and gyroscopes) may introduce privacy issues or require people to wear sensors. To address these issues, recent approaches exploit fine-grained wireless signals for activity recognition. However, these approaches require devices that are costly or need to provide unique wireless features (e.g., Doppler shifts or phase information). With the increasingly available Internet of Things (IoT) devices, in this paper, we propose Harmony, a human activity recognition and monitoring middleware which can utilize the coarse-grained (but pervasively available) received signal strength (RSS) measurements from the radios of IoT devices. We implement a complete evaluation platform (from data collection to data analysis) of the middleware on top of low cost ZigBee compliant MICAz nodes and a laptop. We also conducted extensive experiments. Our results show that our design can achieve similar accuracy as fine-grained WiFi channel state information (CSI) measurement-based approaches. Specifically, our overall human activities recognition accuracy is up to 74% and 90% for RSS readings from a single pair and 3 pairs of IoT devices, respectively.

Initial Consonant Mutation in Scottish Gaelic is considered to be morphological, somewhat idiosyncratic, and neutralizing, that is merging either the mutated sound and some underlying sound or merging two mutated sounds. This study explores articulation in one class of mutation, called Lenition (also Aspiration), asking the question of whether these sounds are articulated in the same fashion or not. Comparison of relevant ultrasound images collected from 3 native speakers of Scottish Gaelic shows that speakers maintain distinctions between True Lenition and False Lenition, suggesting that there is incomplete neutralization. Furthermore, when Lenition of two distinct sounds converge on the same target, subjects again keep the two articulations distinct. These results are consistent with a phonological model which distinguishes between surface forms corresponding to different sources, showing very little complete articulatory neutralisation. Index Terms: articulatory phonetics, ultrasound, lenition, Scottish Gaelic, consonant mutation