Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over the context, then assigns each step to program-based or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and fine-tuning methods. GPT-3.5-Turbo following Plan-then-Reason framework surpasses other prompting baselines without self-consistency while using less API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of fine-tuning with this framework. We present ProTrix model family by finetuning models on TrixInstruct. Our experiments show that ProTrix family generalizes to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that ProTrix can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We open-source our dataset and models at https://github.com/WilliamZR/ProTrix.

Cognitive scientists have long sought to understand what makes some sentences more difficult to comprehend than others. Any account of language comprehension, researchers believe, would benefit from understanding difficulties in comprehension. In recent years researchers successfully developed two models explaining two significant types of difficulty in understanding and producing sentences. While these models successfully predict specific patterns of comprehension difficulties, their predictions are limited and don't fully match results from behavioral experiments. Moreover, until recently researchers couldn't integrate these two models into a coherent account. A new study led by researchers from MIT's Department of Brain and Cognitive Sciences (BCS) now provides such a unified account for difficulties in language comprehension.

Semantic feature models have become a popular tool for prediction and interpretation of fMRI data. In particular, prior work has shown that differences in the fMRI patterns in sentence reading can be explained by context-dependent changes in the semantic feature representations of the words. However, whether the subjects are aware of such changes and agree with them has been an open question. This paper aims to answer this question through a human-subject study. Subjects were asked to judge how the word change from their generic meaning when the words were used in specific sentences. The judgements were consistent with the model predictions well above chance. Thus, the results support the hypothesis that word meaning change systematically depending on sentence context.

Microsoft has officially acquired the makers of predictive keyboard mobile app SwiftKey. The London-based start-up behind the app has been brought into the Microsoft fold in a deal worth an estimated $250 million (£174m). Microsoft is believed to have a keen interest in the firm's artificial intelligence research, including its recently launched Neural Alpha app, which could make its Cortana assistant more accurate. The London-based start-up behind the SwiftKey predictive keyboard app (pictured) has been bought by Microsoft in a deal worth $250 million (£174m). The app is available in over 100 languages, including Arabic, Russian, Thai and Afrikaans, and predicts text as it learns from the user's swipes and key strokes SwiftKey was started by Cambridge graduates in 2008, launching its predictive auto-correcting keyboard app on Android in 2010 and iOS in 2014.